© 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. 26650
    Prev
    Next
    INDEX
    Explanations

    out, up, down

    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
    ↵↵
    -1.52
    J
    -1.48
    _
    -1.38
    Z
    -1.30
    G
    -1.30
    B
    -1.23
    re
    -1.23
    (
    -1.22
     /
    -1.21
    ess
    -1.20
    POSITIVE LOGITS
     into
    1.70
     as
    1.55
    jewelry
    1.54
    bracelet
    1.49
    🤓
    1.48
     to
    1.47
     by
    1.46
     before
    1.46
    珪
    1.45
    pineapple
    1.45
    Activations Density 0.030%

    No Known Activations