© 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. 64936
    Prev
    Next
    INDEX
    Explanations

    description of related art

    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
    женская
    -1.59
    鸩
    -1.55
     bará
    -1.45
     Agrega
    -1.42
     Lleva
    -1.37
     circunstancia
    -1.35
     Seleccione
    -1.33
     Incluye
    -1.32
    はもちろん
    -1.32
     hebt
    -1.30
    POSITIVE LOGITS
    </i>
    1.69
    THE
    1.64
    </strong>
    1.63
    ０
    1.59
    一般的な
    1.55
    M
    1.54
    </em>
    1.48
    </h3>
    1.44
    which
    1.43
     anderes
    1.43
    Activations Density 0.002%

    No Known Activations