Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 35329
    Prev
    Next
    INDEX
    Explanations

    javascript, python, web related terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    r
    1.42
    that
    1.27
    ну
    1.09
    la
    1.09
    m
    1.06
    the
    1.05
    ны
    0.99
    м
    0.99
    st
    0.98
    should
    0.98
    POSITIVE LOGITS
    cco
    0.91
    cción
    0.89
    getic
    0.80
    ffekt
    0.77
    hwar
    0.76
    instellungen
    0.75
    konom
    0.75
    volent
    0.74
    chten
    0.71
    ktiv
    0.71
    Activations Density 0.112%

    No Known Activations