© 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. 189211
    Prev
    Next
    INDEX
    Explanations

    profiling based

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

    counting or amounts

    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
    يدة
    0.51
     لیون
    0.50
    次は
    0.50
    人は
    0.48
     médiane
    0.46
    кистон
    0.46
     ===========
    0.45
    がある
    0.44
    εδ
    0.44
    ريقه
    0.44
    POSITIVE LOGITS
    i
    0.59
     Bahamas
    0.51
     drinking
    0.50
     Recycling
    0.47
     voed
    0.46
    agua
    0.45
    hydration
    0.45
     WATER
    0.43
     drinks
    0.43
     ಆಹಾರ
    0.43
    Activations Density 0.000%

    No Known Activations