© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74911
    Prev
    Next
    INDEX
    Explanations

    members of my family and friends

    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
     that
    -1.73
    ></
    -1.52
     você
    -1.45
     because
    -1.43
     deň
    -1.41
    tività
    -1.34
     herhangi
    -1.31
     vivía
    -1.31
     décembre
    -1.30
     vistazo
    -1.30
    POSITIVE LOGITS
     of
    1.63
     and
    1.46
    👫
    1.31
     have
    1.27
     inol
    1.26
     from
    1.23
     中身
    1.19
    ਠ
    1.19
    aconda
    1.17
     otrzyma
    1.17
    Activations Density 0.037%

    No Known Activations