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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 5822
    Prev
    Next
    INDEX
    Explanations

    communication and computation

    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_22_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
    .”[
    0.62
    <em>
    0.60
    <sup>
    0.59
    <strong>
    0.57
    <u>
    0.57
    <i>
    0.55
    )—
    0.55
    ”—
    0.55
    <b>
    0.53
    “[
    0.53
    POSITIVE LOGITS
     gpu
    0.74
     idx
    0.73
     dataframe
    0.73
     fake
    0.71
     cpu
    0.69
     regex
    0.68
     这里
    0.67
     dummy
    0.67
     update
    0.66
     user
    0.65
    Activations Density 2.751%

    No Known Activations