© 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. 34105
    Prev
    Next
    INDEX
    Explanations

    property listings

    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
     and
    -1.63
     because
    -1.52
     ponieważ
    -1.34
     often
    -1.25
     also
    -1.24
     commonly
    -1.24
     in
    -1.21
     large
    -1.17
     Many
    -1.17
     which
    -1.16
    POSITIVE LOGITS
     весьма
    1.65
     réjou
    1.38
     esfuer
    1.33
    菒
    1.33
    荦
    1.32
    没能
    1.31
     récla
    1.29
    BTW
    1.27
     aimable
    1.26
     appré
    1.25
    Activations Density 0.238%

    No Known Activations