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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 933
    Prev
    Next
    INDEX
    Explanations

    levels and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
     reflectance
    0.81
    QMainWindow
    0.76
     setattr
    0.76
     હાઉસ
    0.69
    便
    0.67
     fates
    0.66
    装
    0.65
     investigative
    0.65
    վ
    0.64
     shading
    0.64
    POSITIVE LOGITS
    Baba
    0.91
    azim
    0.86
    ディース
    0.84
    germ
    0.83
    agina
    0.83
     GERM
    0.82
    Germ
    0.81
    Concent
    0.80
     Garten
    0.80
     lép
    0.80
    Activations Density 0.000%

    No Known Activations