© 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. 59649
    Prev
    Next
    INDEX
    Explanations

    method calls with parameters

    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
    0
    -1.58
    1
    -1.57
    ⡪
    -1.55
    对付
    -1.50
     firmado
    -1.47
    SARAH
    -1.46
     válasz
    -1.45
     てき
    -1.44
     tanul
    -1.43
    zate
    -1.41
    POSITIVE LOGITS
    MA
    1.67
    (
    1.66
     Japão
    1.50
    Not
    1.42
    𝗦
    1.41
    (´
    1.40
    ˗
    1.39
     coração
    1.38
     of
    1.36
    не
    1.36
    Activations Density 0.001%

    No Known Activations