© 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. 66345
    Prev
    Next
    INDEX
    Explanations

    BTC donations

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

    look what i did

    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
    ă
    0.52
     moto
    0.50
     kõ
    0.49
     emir
    0.49
     schwe
    0.48
     dnia
    0.47
     zenith
    0.47
     hight
    0.47
     eksp
    0.46
    сім
    0.46
    POSITIVE LOGITS
    喿
    0.57
     सीजीएल
    0.50
    傊
    0.47
    ాను
    0.45
    rtList
    0.44
     ansiedad
    0.44
    㝒
    0.43
    Carlo
    0.43
    Stewart
    0.43
     நன்க
    0.43
    Activations Density 0.000%

    No Known Activations