© 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. 15419
    Prev
    Next
    INDEX
    Explanations

    introductions and explanations

    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
     récemment
    -1.41
     навіть
    -1.20
    殽
    -1.18
     vermelho
    -1.16
    ेन
    -1.11
    綺麗
    -1.10
     plateado
    -1.10
    ཿ
    -1.10
     seleccionadas
    -1.09
     Albans
    -1.08
    POSITIVE LOGITS
     how
    1.71
     about
    1.55
     which
    1.54
     who
    1.40
    </th>
    1.30
    </i>
    1.28
     with
    1.27
    ÁT
    1.23
     if
    1.22
    </h1>
    1.19
    Activations Density 0.036%

    No Known Activations