© 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. 3816
    Prev
    Next
    INDEX
    Explanations

    selecting clinical diagnoses

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

    code or programming language elements, particularly in markup and script files.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is activated by backslash‐initiated hexadecimal escape sequences (e.g. “\x0a”).

    oai_token-act-pair · o4-miniTriggered 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
     comportements
    -1.67
     этой
    -1.60
    ἵ
    -1.43
    </em>
    -1.42
    groet
    -1.41
    </i>
    -1.39
     эту
    -1.37
     faciliter
    -1.32
     spezi
    -1.27
     einheit
    -1.27
    POSITIVE LOGITS
     but
    2.52
     there
    1.92
     when
    1.74
     although
    1.63
     trattano
    1.58
     had
    1.57
    órica
    1.52
    なんですが
    1.51
     However
    1.42
     Although
    1.41
    Activations Density 0.002%

    No Known Activations