© 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. 71619
    Prev
    Next
    INDEX
    Explanations

    names starting with initials

    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
    不断的
    -1.73
    あえて
    -1.70
     liberdade
    -1.51
    あっという
    -1.41
    お昼
    -1.40
     our
    -1.38
    というわけで
    -1.36
     informaron
    -1.34
    よな
    -1.34
    现在的
    -1.33
    POSITIVE LOGITS
    There
    1.65
     there
    1.56
    niques
    1.46
    散文
    1.45
    ToProps
    1.45
    ůměr
    1.43
    YNAMIC
    1.38
    ingabe
    1.37
     displayed
    1.34
    oherty
    1.34
    Activations Density 0.096%

    No Known Activations