© 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. 54354
    Prev
    Next
    INDEX
    Explanations

    the words

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

    specific details or limitations

    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
    ic
    0.46
    m
    0.43
    ik
    0.40
    í
    0.40
    im
    0.40
     renov
    0.40
    J
    0.40
    oches
    0.38
    C
    0.38
    V
    0.38
    POSITIVE LOGITS
     ብዙውን
    0.57
    бычно
    0.55
    teams
    0.54
     Обычно
    0.52
    вшей
    0.49
     particolari
    0.47
    ScriptBuf
    0.47
     продукти
    0.47
    வுகளை
    0.46
     चीजों
    0.46
    Activations Density 0.000%

    No Known Activations