© 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. 39149
    Prev
    Next
    INDEX
    Explanations

    file paths and directory names

    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
    {
    -4.19
    \
    -2.69
    $
    -2.45
    ``
    -2.23
    ("
    -2.22
    ()
    -2.16
     {
    -2.11
    葑
    -2.08
    E
    -2.08
     t
    -2.08
    POSITIVE LOGITS
    媖
    2.61
    ࿙
    2.58
    ’，
    2.38
    .”
    2.36
     anderen
    2.36
    婬
    2.34
    ?
    2.30
    ing
    2.30
     musées
    2.23
     involucrados
    2.19
    Activations Density 0.003%

    No Known Activations