© 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. 204277
    Prev
    Next
    INDEX
    Explanations

    .xls format

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

    conditional formulas and commands

    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
     kawa
    0.48
    ഡ്
    0.46
     `--
    0.46
     wisatawan
    0.46
     estet
    0.46
     Boogie
    0.45
     Corvette
    0.45
     считаю
    0.43
     adip
    0.42
     burb
    0.42
    POSITIVE LOGITS
    $('#
    0.44
     प्रस्तुत
    0.43
    기의
    0.42
    न्तु
    0.42
    eneration
    0.41
    যারা
    0.41
    να
    0.41
    inguished
    0.41
    Wu
    0.41
     troubled
    0.41
    Activations Density 0.001%

    No Known Activations