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. 19629
    Prev
    Next
    INDEX
    Explanations

    current or modern states

    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
    ็ด
    0.78
    ności
    0.71
     Witten
    0.71
     Prosecutors
    0.71
    あって
    0.70
     THROUGH
    0.69
     wij
    0.68
     들
    0.68
    iers
    0.68
     Nicht
    0.68
    POSITIVE LOGITS
    最多
    0.82
     очеред
    0.80
     flourishes
    0.77
     современных
    0.77
     நவீன
    0.75
    Hiện
    0.75
     todays
    0.74
     جریان
    0.73
    QTY
    0.72
     Hiện
    0.72
    Activations Density 0.000%

    No Known Activations