© 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. 63914
    Prev
    Next
    INDEX
    Explanations

    continues reading

    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
    body
    -0.95
    Body
    -0.87
    cap
    -0.78
    мира
    -0.78
    aron
    -0.77
    готовка
    -0.75
    rent
    -0.74
     Maior
    -0.74
    Model
    -0.74
    conv
    -0.73
    POSITIVE LOGITS
     świat
    0.79
     отвечает
    0.76
     reducción
    0.76
    خخ
    0.75
     dâu
    0.75
    mandala
    0.73
     końca
    0.73
    練習
    0.72
    tiglia
    0.72
    нились
    0.72
    Activations Density 0.002%

    No Known Activations