© 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. 128327
    Prev
    Next
    INDEX
    Explanations

    opinion of \\

    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
     crux
    -1.65
     are
    -1.63
    今も
    -1.55
    </b>
    -1.52
     Extremely
    -1.46
    来到了
    -1.45
     Relatively
    -1.45
     proclaim
    -1.45
    ┉
    -1.44
     ahora
    -1.43
    POSITIVE LOGITS
    𞤢
    2.08
    衕
    1.81
     dieu
    1.64
     墊
    1.59
     jue
    1.58
    栳
    1.56
    tionally
    1.54
     UNIVER
    1.52
    УДК
    1.52
     loi
    1.52
    Activations Density 0.037%

    No Known Activations