© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 89909
    Prev
    Next
    INDEX
    Explanations

    punctuation and list separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     réalisés
    0.47
    つける
    0.47
    를
    0.46
    ρώ
    0.45
    と
    0.45
    ='.
    0.44
    σω
    0.44
    と感じ
    0.44
    🤢
    0.43
    дан
    0.43
    POSITIVE LOGITS
    했지만
    0.48
     rpm
    0.46
    <0x0D>
    0.44
     agam
    0.43
     JHEP
    0.43
     हेमा
    0.43
     hubo
    0.42
     الاثنين
    0.42
     stata
    0.41
     berc
    0.41
    Activations Density 0.001%

    No Known Activations