© 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. 27385
    Prev
    Next
    INDEX
    Explanations

    home city

    np_acts-logits-general · gemini-2.5-flash-lite

    end of phrase delimiters

    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
    ті
    0.55
     were
    0.53
     hocam
    0.53
    Thank
    0.48
    Were
    0.48
    IsIn
    0.48
    აძ
    0.47
    렀
    0.47
    hagen
    0.47
    라이언트
    0.46
    POSITIVE LOGITS
     Translations
    0.47
     Cumulative
    0.46
     Including
    0.45
     நிறு
    0.45
     Electricity
    0.43
     Wide
    0.43
     Trades
    0.43
     Accumulated
    0.43
     And
    0.43
     Personal
    0.43
    Activations Density 0.000%

    No Known Activations