© 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. 10-GEMMASCOPE-RES-131K
    7. 102526
    Prev
    Next
    INDEX
    Explanations

    size and dimensions

    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_10/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
    <bos>
    -1.70
    はこの
    -1.66
     extracción
    -1.56
    enfance
    -1.52
     seleccionamos
    -1.52
    內容簡介
    -1.45
    })$,
    -1.42
    ambassade
    -1.41
     sebagainya
    -1.41
     BEFORE
    -1.40
    POSITIVE LOGITS
     of
    2.16
    0
    1.83
    !
    1.50
    遑
    1.49
    e
    1.46
     the
    1.45
    ang
    1.44
    c
    1.41
     acreditar
    1.40
    ol
    1.39
    Activations Density 0.001%

    No Known Activations