© 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. 10-GEMMASCOPE-RES-131K
    7. 113142
    Prev
    Next
    INDEX
    Explanations

    the word appearance

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

    The neuron fires strongly on occurrences of the word “appearance.”

    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
    镦
    -3.22
    硨
    -2.83
    鬭
    -2.69
     There
    -2.52
    錞
    -2.47
     voleva
    -2.38
    ?"
    -2.31
     At
    -2.31
    тку
    -2.30
    気づ
    -2.30
    POSITIVE LOGITS
    鲩
    3.20
    弍
    2.94
    汭
    2.89
    ↵↵
    2.86
    おわりに
    2.84
    
    2.83
    趼
    2.72
    ↵
    2.69
     больших
    2.64
    varlak
    2.61
    Activations Density 0.005%

    No Known Activations