© 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. 110839
    Prev
    Next
    INDEX
    Explanations

    competition results and tasks done

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

    lists of items

    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
    Twin
    0.47
    ich
    0.47
    也会
    0.43
    Spor
    0.43
    ஜ
    0.43
     pouvant
    0.42
     Kand
    0.41
    Fleet
    0.41
    wnież
    0.41
    จำนวน
    0.41
    POSITIVE LOGITS
     ﺍ
    0.48
     armas
    0.47
     વાળ
    0.45
     quên
    0.45
     agric
    0.45
     arma
    0.45
     bagels
    0.44
     шко
    0.43
     tóc
    0.43
     dilwale
    0.43
    Activations Density 0.001%

    No Known Activations