© 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. 22-GEMMASCOPE-RES-131K
    7. 64721
    Prev
    Next
    INDEX
    Explanations

    programming calls and technical descriptions

    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
     for
    -1.56
     população
    -1.45
     legislación
    -1.40
    ísimas
    -1.38
    рою
    -1.36
     dikirim
    -1.34
    (!__
    -1.32
    yled
    -1.32
     জন্য
    -1.31
     manhã
    -1.30
    POSITIVE LOGITS
    (
    2.30
    You
    1.59
    [
    1.55
    No
    1.53
    '
    1.45
     (
    1.41
     what
    1.39
    S
    1.38
    -
    1.36
    ?
    1.36
    Activations Density 0.001%

    No Known Activations