© 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. 115659
    Prev
    Next
    INDEX
    Explanations

    figure followed by number

    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
     ratusan
    -0.90
     sample
    -0.82
     didat
    -0.81
     armon
    -0.81
    党的
    -0.80
     still
    -0.79
     competen
    -0.79
    ibili
    -0.78
     cintura
    -0.77
    asymp
    -0.77
    POSITIVE LOGITS
    емости
    0.80
    闕
    0.78
     mediocrity
    0.77
    Vx
    0.77
    Levi
    0.76
    дьба
    0.75
     illustrator
    0.74
    eleven
    0.73
    Draws
    0.73
     requieren
    0.73
    Activations Density 0.004%

    No Known Activations