© 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. 15508
    Prev
    Next
    INDEX
    Explanations

    parts of words

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

    how one might approach

    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
    িনী
    0.55
    鳳
    0.51
    圓
    0.48
     jedną
    0.47
    単
    0.47
     ある
    0.47
    ណ៌
    0.47
    uksia
    0.47
    льзу
    0.46
    並
    0.46
    POSITIVE LOGITS
    했지만
    0.48
     इसने
    0.44
    kenn
    0.44
     atr
    0.43
    shelf
    0.42
     cursive
    0.42
     जिसने
    0.42
    o
    0.42
    でしたが
    0.41
    вец
    0.41
    Activations Density 0.000%

    No Known Activations