© 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. 22-GEMMASCOPE-RES-131K
    7. 129274
    Prev
    Next
    INDEX
    Explanations

    configuration keys or labels

    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_22/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
    <?
    -1.02
    ,
    -0.85
     فاصله
    -0.85
     with
    -0.84
     открыть
    -0.83
    /*!
    -0.83
     was
    -0.81
    思索
    -0.80
     isn
    -0.79
    rrggbb
    -0.79
    POSITIVE LOGITS
    Lokasi
    1.12
    Когда
    1.10
    Harga
    1.01
    Бе
    1.00
     necesarios
    0.98
    Описание
    0.97
     MUNDO
    0.97
    ところは
    0.97
    Might
    0.96
     adecuados
    0.96
    Activations Density 0.022%

    No Known Activations