© 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. 129401
    Prev
    Next
    INDEX
    Explanations

    program names and websites

    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
     conster
    -1.27
     faciliter
    -1.26
     procla
    -1.22
    馓
    -1.20
    brtc
    -1.19
     entret
    -1.18
    COMPR
    -1.17
     levant
    -1.17
    儅
    -1.16
     beij
    -1.16
    POSITIVE LOGITS
     That
    1.42
     Some
    1.41
     some
    1.39
     used
    1.35
     Even
    1.34
     Like
    1.31
    Some
    1.30
     What
    1.29
     Just
    1.29
     Not
    1.25
    Activations Density 0.130%

    No Known Activations