© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 3398
    Prev
    Next
    INDEX
    Explanations

    Consider or single respond

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    cf
    0.49
    ->_
    0.49
    ทยาลัย
    0.49
     dependencies
    0.48
    কে
    0.48
    t
    0.47
     এ
    0.46
    api
    0.44
     superson
    0.44
     :/
    0.44
    POSITIVE LOGITS
    Processed
    0.45
     loa
    0.43
    startIndex
    0.42
     footprint
    0.41
    itical
    0.41
    ազմ
    0.39
     footprints
    0.39
    STS
    0.39
     تحليل
    0.38
    鞠
    0.38
    Activations Density 0.000%

    No Known Activations