© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78819
    Prev
    Next
    INDEX
    Explanations

    central government or authoritarian tactics

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

    The neuron fires on substantive content words (not function words)—especially rarer nouns and adjectives that carry thematic or technical meaning.

    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
    立马
    -1.27
     insieme
    -1.19
     우리
    -1.13
    ㎡
    -1.12
    (){
    -1.09
     toti
    -1.09
    ᴮ
    -1.08
     crevices
    -1.05
     déjeuner
    -1.04
    ************/
    -1.04
    POSITIVE LOGITS
     foodstuffs
    1.30
     PCs
    1.03
    OOC
    1.02
    Rumors
    0.99
     durchführen
    0.98
     or
    0.96
    Ѕ
    0.94
    ॄ
    0.93
    lizia
    0.93
     utterly
    0.91
    Activations Density 0.044%

    No Known Activations