© 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. 14890
    Prev
    Next
    INDEX
    Explanations

    kick into overdrive or high gear

    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
    بق
    0.73
     integrals
    0.72
     тут
    0.71
     поверхности
    0.63
     cakes
    0.62
     displace
    0.62
     B
    0.61
     cats
    0.61
     perk
    0.60
     tack
    0.60
    POSITIVE LOGITS
    একটি
    0.97
     deletion
    0.90
     pickled
    0.86
    ToBe
    0.85
     পাত
    0.84
    Israeli
    0.84
    routingHeader
    0.83
    teenage
    0.83
    ྵ
    0.83
    Elliott
    0.83
    Activations Density 0.000%

    No Known Activations