© 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. 33750
    Prev
    Next
    INDEX
    Explanations

    if defined macros

    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
     alcune
    -1.50
    ’:
    -1.45
    ’
    -1.42
    *************/
    -1.41
    ኗ
    -1.38
    矬
    -1.33
    を行いました
    -1.31
    ************/
    -1.30
     doua
    -1.26
     другие
    -1.25
    POSITIVE LOGITS
     or
    1.94
     alebo
    1.81
     at
    1.76
     of
    1.67
    '
    1.62
     (
    1.48
     spørsmål
    1.48
     to
    1.43
    </strong>
    1.37
     in
    1.35
    Activations Density 0.003%

    No Known Activations