© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39263
    Prev
    Next
    INDEX
    Explanations

    settings and configuration

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron spotlights occurrences of “Settings” (and similarly labeled configuration or options identifiers) in code or markup.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    references to software configuration and preferences (e.g., settings/options) in code and config metadata.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the word "settings" or "Settings" in code, particularly in import statements, class names, and configuration contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </sup>
    -1.52
     our
    -1.43
    SetId
    -1.42
     لنا
    -1.38
     '
    -1.34
     those
    -1.32
    ESSION
    -1.31
    よろしくお願いします
    -1.31
    would
    -1.31
    ACING
    -1.30
    POSITIVE LOGITS
     regarding
    1.70
     AQUI
    1.64
     about
    1.62
     there
    1.58
     concerning
    1.51
     which
    1.41
    媜
    1.39
     imóvel
    1.38
     Paramètres
    1.38
     EXERC
    1.37
    Activations Density 0.045%

    No Known Activations