© 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. 26807
    Prev
    Next
    INDEX
    Explanations

    people who knew

    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
     its
    -1.91
    ølge
    -1.58
    日時
    -1.54
    unción
    -1.44
    ldquo
    -1.34
    -};
    -1.32
    Its
    -1.30
     sánh
    -1.30
    Når
    -1.30
     οποίο
    -1.29
    POSITIVE LOGITS
     [
    2.53
     
    1.60
     we
    1.40
    [
    1.29
    '
    1.28
    0
    1.27
     (
    1.22
    6
    1.22
     people
    1.21
    2
    1.13
    Activations Density 0.048%

    No Known Activations