© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 128907
    Prev
    Next
    INDEX
    Explanations

    foreign names or titles

    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
    -4.31
     or
    -3.52
     of
    -3.34
     from
    -3.19
     at
    -3.08
     on
    -2.97
     with
    -2.84
     by
    -2.72
     as
    -2.63
     for
    -2.59
    POSITIVE LOGITS
    骉
    2.39
     myriad
    2.30
    several
    2.22
     acclaimed
    2.11
    being
    2.11
     wondrous
    2.11
     dando
    2.09
    almost
    2.09
    ong
    2.08
    ⎔
    2.08
    Activations Density 0.129%

    No Known Activations