© 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. 33361
    Prev
    Next
    INDEX
    Explanations

    size, position, shape, time

    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
     Jahrgang
    -1.23
    程序
    -1.16
     mereka
    -1.09
    ༼
    -1.08
    ícia
    -1.08
    brainer
    -1.08
    ються
    -1.05
    ваются
    -1.05
    sierten
    -1.05
    每个
    -1.03
    POSITIVE LOGITS
    了几
    1.05
     nuevamente
    1.05
    Mvh
    1.04
    .
    1.03
    <bos>
    1.00
     aceptas
    0.99
     riv
    0.98
    strzy
    0.96
     northwestern
    0.96
     supuestamente
    0.96
    Activations Density 0.001%

    No Known Activations