© 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. 903
    Prev
    Next
    INDEX
    Explanations

    variety of

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

    write a

    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
    iają
    0.46
     इजा
    0.44
    วาม
    0.43
    íj
    0.43
    典型的
    0.43
    <unused1741>
    0.43
    ியுள்ள
    0.42
    ávan
    0.42
    ávají
    0.42
    Minn
    0.42
    POSITIVE LOGITS
    :
    0.48
    кле
    0.47
     blame
    0.47
    ッジ
    0.46
     Bisch
    0.46
    ert
    0.46
    クリア
    0.46
    ମ୍
    0.46
     فرق
    0.46
    について
    0.45
    Activations Density 0.000%

    No Known Activations