© 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. 236751
    Prev
    Next
    INDEX
    Explanations

    reading glasses

    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
     preparado
    0.45
    นะครับ
    0.44
     série
    0.43
    лли
    0.43
    ЛА
    0.42
     سلسلے
    0.42
    MOVIE
    0.42
    🍌
    0.42
     seterusnya
    0.41
    ˁ
    0.41
    POSITIVE LOGITS
     causes
    0.46
     Gad
    0.45
     Causes
    0.45
     doorbell
    0.44
     examiner
    0.44
     Wenn
    0.43
     Weyl
    0.43
     লাভের
    0.42
     Esther
    0.42
     profitieren
    0.42
    Activations Density 0.001%

    No Known Activations