© 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. 22-GEMMASCOPE-RES-131K
    7. 13995
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
    ごとの
    -1.52
    に入れる
    -1.48
     bijzondere
    -1.45
     coûts
    -1.38
     verschillende
    -1.34
    indicate
    -1.34
     vijf
    -1.31
     goederen
    -1.30
    mitglieder
    -1.27
    bisa
    -1.27
    POSITIVE LOGITS
     in
    2.16
     to
    1.75
     (
    1.73
    がある
    1.65
    があります
    1.61
     with
    1.54
     at
    1.49
     on
    1.48
     mostly
    1.45
     around
    1.44
    Activations Density 0.020%

    No Known Activations