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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 86002
    Prev
    Next
    INDEX
    Explanations

    !important CSS directives

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

    This neuron flags non‐alphanumeric code symbols—punctuation tokens (like “:”, “!”, “@”) and other operator or decorator markers in source code.

    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
     détaillée
    -1.47
    álogo
    -1.47
     pertama
    -1.45
    vedades
    -1.38
     første
    -1.38
    tagHelper
    -1.35
    ’
    -1.34
    ')(
    -1.33
     första
    -1.32
    }}:
    -1.30
    POSITIVE LOGITS
    t
    1.72
     of
    1.46
    y
    1.34
     ,‬
    1.29
    u
    1.27
    e
    1.23
    にほんブログ村
    1.18
     emphatically
    1.12
    al
    1.09
    よな
    1.09
    Activations Density 0.009%

    No Known Activations