© 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. 2873
    Prev
    Next
    INDEX
    Explanations

    #include and copyright comments

    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
     Saltar
    -0.89
     câbles
    -0.79
     FUCK
    -0.76
     quartiers
    -0.76
     Obtener
    -0.75
     вообще
    -0.74
     Cár
    -0.74
     @[
    -0.74
    lma
    -0.74
     Syrie
    -0.72
    POSITIVE LOGITS
     prime
    0.85
     تمرین
    0.77
    chart
    0.77
    issy
    0.76
    prime
    0.75
    charset
    0.75
     rush
    0.74
     ха
    0.73
    իլ
    0.73
    validates
    0.72
    Activations Density 0.003%

    No Known Activations