© 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. 85331
    Prev
    Next
    INDEX
    Explanations

    lemon and its pairings

    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_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
     But
    -3.38
    .”
    -2.86
     selben
    -2.70
    ,’’
    -2.69
    不管是
    -2.56
     チェア
    -2.52
    真的
    -2.50
    ﮏ
    -2.45
    indelijk
    -2.45
     necessaria
    -2.42
    POSITIVE LOGITS
    the
    3.31
    .
    2.84
    鸶
    2.50
    쩡
    2.44
    骉
    2.41
    
    2.31
    襤
    2.30
    垟
    2.30
     شهرهای
    2.27
    тол
    2.27
    Activations Density 0.002%

    No Known Activations