© 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. 34-GEMMASCOPE-RES-131K
    7. 47907
    Prev
    Next
    INDEX
    Explanations

    Indian politicians and news

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

    The neuron consistently fires on common grammatical “function” words—short, high‐frequency tokens like pronouns, prepositions, auxiliaries, and articles.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    NEM
    -0.94
    令和
    -0.87
     حتی
    -0.82
     tendance
    -0.81
    ACKS
    -0.81
    streifen
    -0.81
     Arteta
    -0.79
     Bolsonaro
    -0.78
     esco
    -0.78
    https
    -0.78
    POSITIVE LOGITS
     Sonia
    0.95
     diesel
    0.87
    UPA
    0.85
     Congress
    0.84
    RectF
    0.82
     Coal
    0.79
    一趟
    0.79
    ໒
    0.79
     coal
    0.78
     Sahara
    0.77
    Activations Density 0.042%

    No Known Activations