© 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. 1956
    Prev
    Next
    INDEX
    Explanations

    numerical units and time

    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
    ی
    1.50
    RUTA
    1.31
    রাষ্ট্রে
    1.30
     mAbs
    1.29
    iada
    1.29
     trot
    1.28
    ië
    1.28
     mAb
    1.23
     distractions
    1.21
     dispensers
    1.21
    POSITIVE LOGITS
    ज
    1.14
     lagi
    0.92
    これ
    0.92
     зна
    0.91
     यूरोप
    0.91
    fortunately
    0.87
    trat
    0.87
    cnt
    0.85
    supp
    0.84
     साइनस
    0.83
    Activations Density 0.000%

    No Known Activations