© 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. 10-GEMMASCOPE-RES-131K
    7. 44071
    Prev
    Next
    INDEX
    Explanations

    accessories, accessorizing, belt, or buckle

    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_10/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
    handleClose
    -1.15
    (+
    -1.12
     ajuda
    -1.09
     intérêts
    -1.09
    =/
    -1.05
     blueprint
    -1.05
    rebel
    -1.04
    intérêt
    -1.04
    дыду
    -1.03
    neho
    -1.02
    POSITIVE LOGITS
    </i>
    1.41
    tête
    1.27
    原来的
    1.26
    чений
    1.25
    colazione
    1.23
    </u>
    1.23
     nécessaires
    1.23
    ineros
    1.21
    aryan
    1.20
    できなかった
    1.20
    Activations Density 0.026%

    No Known Activations