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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 809
    Prev
    Next
    INDEX
    Explanations

    start of quotation

    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
     "
    1.07
    ("
    0.94
     ("
    0.93
    ("-
    0.86
    {"
    0.85
     also
    0.84
    )["
    0.84
    ↵
    0.81
    —“
    0.79
    /"
    0.79
    POSITIVE LOGITS
    It
    1.54
    Every
    1.46
    There
    1.44
    We
    1.42
    They
    1.41
    These
    1.35
    Congratulations
    1.35
    Our
    1.33
    Sometimes
    1.32
    This
    1.31
    Activations Density 0.048%

    No Known Activations