© 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. 82762
    Prev
    Next
    INDEX
    Explanations

    not implemented exceptions

    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_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
     куро
    -0.87
    merzen
    -0.81
     gynnwys
    -0.80
     turquesa
    -0.79
     terakhir
    -0.77
    経緯
    -0.74
    という感じ
    -0.74
    isFirst
    -0.74
    Battlefield
    -0.73
    Referees
    -0.73
    POSITIVE LOGITS
     NotImplemented
    2.08
    NotImplemented
    2.00
     implement
    1.56
     implementation
    1.52
    implemented
    1.49
     implemented
    1.47
     TODO
    1.47
     Implement
    1.43
    implement
    1.43
    todo
    1.35
    Activations Density 0.008%

    No Known Activations