© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 33753
    Prev
    Next
    INDEX
    Explanations

    evaluation of properties

    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
    liğ
    -1.23
     aussehen
    -1.05
    xhttp
    -1.02
    have
    -1.02
    allery
    -1.02
    一些
    -0.99
     الشخص
    -0.98
    ところ
    -0.98
     ストレッチ
    -0.98
     Conexion
    -0.98
    POSITIVE LOGITS
     by
    2.25
     using
    2.05
     in
    2.00
     through
    1.73
     via
    1.69
     of
    1.41
     on
    1.30
     at
    1.28
     based
    1.20
     with
    1.16
    Activations Density 0.231%

    No Known Activations