© 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. 484
    Prev
    Next
    INDEX
    Explanations

    view

    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
    ма
    1.10
    джа
    0.98
     의해
    0.96
     fract
    0.94
    ાઈ
    0.92
    ت
    0.92
    ція
    0.89
    asında
    0.88
    Ста
    0.87
    жан
    0.87
    POSITIVE LOGITS
    point
    1.68
    ports
    1.48
     👀
    1.46
     xét
    1.45
    HasStarred
    1.43
     exposureButton
    1.41
     plonge
    1.36
    StubCompat
    1.35
    WillAppear
    1.33
    points
    1.31
    Activations Density 0.058%

    No Known Activations