© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 19265
    Prev
    Next
    INDEX
    Explanations

    wild card, Wild West

    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
     idk
    1.16
    KPI
    1.15
    ܢܐ
    1.11
     valle
    1.10
     заданной
    1.09
    imiento
    1.05
     tick
    1.05
    <unused28>
    1.03
    Consent
    1.03
    ресень
    1.03
    POSITIVE LOGITS
    cards
    1.68
    card
    1.41
    cat
    1.38
    fowl
    1.38
    erness
    1.33
    y
    1.33
    دة
    1.33
    ा
    1.31
    flowers
    1.24
    er
    1.20
    Activations Density 0.013%

    No Known Activations