© 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. 14175
    Prev
    Next
    INDEX
    Explanations

    word counts

    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
     शक्ति
    0.66
     ninguna
    0.65
    uitary
    0.65
    power
    0.62
     range
    0.62
    徎
    0.61
     power
    0.61
     meteorite
    0.61
    force
    0.60
     currently
    0.60
    POSITIVE LOGITS
     IPs
    0.71
     밀
    0.63
     deserts
    0.62
    ㄚ
    0.62
     Flyers
    0.61
     exposição
    0.61
    zą
    0.60
    agę
    0.59
    밀
    0.59
    annotations
    0.59
    Activations Density 0.011%

    No Known Activations