© 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. 25667
    Prev
    Next
    INDEX
    Explanations

    Pauline Moss Amazon

    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
     setelan
    -1.38
    TRIBUN
    -1.38
     Unidades
    -1.37
     consentimento
    -1.33
     retrô
    -1.30
    These
    -1.29
     sarung
    -1.28
     churras
    -1.27
     Melhor
    -1.24
     pesso
    -1.23
    POSITIVE LOGITS
     (
    1.77
    ’
    1.59
    ”
    1.55
    ,
    1.49
    </strong>
    1.41
    -
    1.38
    </u>
    1.38
    <>
    1.34
    “
    1.29
    <u>
    1.26
    Activations Density 0.000%

    No Known Activations