© 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. 179513
    Prev
    Next
    INDEX
    Explanations

    dates and years

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

    as of today, date, reports

    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
     prophylactic
    0.46
    最初は
    0.46
     gặp
    0.44
     Walking
    0.40
    みる
    0.40
    (',');
    0.39
     outset
    0.39
    うちに
    0.39
     Wish
    0.39
     いつ
    0.39
    POSITIVE LOGITS
     ranked
    0.51
    ang
    0.47
    仍在
    0.46
    கிறது
    0.45
    ranked
    0.43
    6
    0.43
     masih
    0.42
    pang
    0.42
    1
    0.42
     рейтинг
    0.41
    Activations Density 0.049%

    No Known Activations