© 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. 42549
    Prev
    Next
    INDEX
    Explanations

    adjusted correctly

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

    closer, preset, Reduction, period, Pun

    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
     난
    0.49
     Arti
    0.47
     চিকিৎসা
    0.45
     모양
    0.43
    aji
    0.43
    apa
    0.43
     기억
    0.43
     なかっ
    0.42
     태
    0.41
    注意事項
    0.41
    POSITIVE LOGITS
    4
    0.43
    DEN
    0.42
    WITH
    0.41
    endif
    0.41
    l
    0.41
    elh
    0.40
    3
    0.39
    ел
    0.39
     fährt
    0.39
     dobu
    0.39
    Activations Density 0.000%

    No Known Activations