© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129702
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on the vote‐count numbers (the numeric scores) that appear after a post, i.e. the standalone score tokens at the end of answers.

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

    third-person pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    They
    -1.08
    Despite
    -0.98
    Over
    -0.93
     exacta
    -0.91
     Даже
    -0.91
    Have
    -0.88
    While
    -0.86
    中には
    -0.85
    Some
    -0.84
    skog
    -0.83
    POSITIVE LOGITS
     his
    2.80
     himself
    2.42
    himself
    1.59
     he
    1.37
     jego
    1.35
     egli
    1.30
     hänen
    1.28
    他的
    1.27
     نفسه
    1.23
     خودش
    1.23
    Activations Density 0.076%

    No Known Activations