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-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 1176
    Prev
    Next
    INDEX
    Explanations

    pronouns, entities, and nouns

    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
     Basics
    1.04
     (*
    1.00
     *(
    0.99
     Applicable
    0.99
     "(
    0.97
     gum
    0.95
     inet
    0.93
     (**
    0.93
     ######
    0.92
     Responses
    0.92
    POSITIVE LOGITS
    He
    1.90
    She
    1.78
    John
    1.72
    Don
    1.71
    The
    1.68
    My
    1.66
    They
    1.63
    It
    1.63
    His
    1.61
    Happy
    1.60
    Activations Density 0.074%

    No Known Activations