© 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. 66125
    Prev
    Next
    INDEX
    Explanations

    variable names, types, or identifiers

    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
     which
    -1.33
    conhe
    -1.24
    LLABLE
    -1.22
     cuidar
    -1.16
     bluza
    -1.16
    gorro
    -1.11
     acrílico
    -1.10
     and
    -1.09
    тивно
    -1.07
     feltro
    -1.07
    POSITIVE LOGITS
    -
    1.37
     -
    1.34
    _
    1.24
    ${
    1.20
    begin
    1.18
    ID
    1.16
     $
    1.16
    u
    1.15
    --
    1.09
    $
    1.06
    Activations Density 0.063%

    No Known Activations