© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 81506
    Prev
    Next
    INDEX
    Explanations

    Wolf followed by compound words

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

    This neuron selectively activates on occurrences of the token “Wolf.”

    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
    (
    -0.79
     schlafen
    -0.75
    用途
    -0.72
     conjuntos
    -0.71
     envie
    -0.69
    マス
    -0.69
     installment
    -0.69
    椅子
    -0.69
     rectangles
    -0.69
     plupart
    -0.68
    POSITIVE LOGITS
     Wol
    1.35
     Wolf
    1.25
     wol
    1.11
    Wol
    1.08
    pack
    1.08
     WOLF
    1.06
    enden
    1.05
     WOL
    1.04
    Wolf
    0.95
    gram
    0.95
    Activations Density 0.015%

    No Known Activations