© 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. 311
    Prev
    Next
    INDEX
    Explanations

    timezone offsets

    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
     minimum
    0.76
    a
    0.75
    ali
    0.69
     gradient
    0.69
     slow
    0.69
     busy
    0.68
     local
    0.68
     weather
    0.67
     starg
    0.66
    olit
    0.66
    POSITIVE LOGITS
    वेस्ट
    0.85
    信任
    0.79
     JMS
    0.78
    Agregar
    0.76
    tbLabel
    0.74
    ServiceObject
    0.74
    <unused1159>
    0.73
     Thành
    0.73
    trashItem
    0.72
     имел
    0.72
    Activations Density 0.000%

    No Known Activations