© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 25312
    Prev
    Next
    INDEX
    Explanations

    background and color properties

    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
    晚餐
    0.44
    鲁
    0.43
    ิลป
    0.41
    poč
    0.41
    ܠ
    0.41
    بوع
    0.40
    épendant
    0.40
     smach
    0.39
    acjach
    0.39
    IRCONIUM
    0.39
    POSITIVE LOGITS
     scanning
    0.44
     Scanning
    0.43
     Seagate
    0.43
     Thailand
    0.42
     Massachusetts
    0.41
     Translation
    0.39
     SE
    0.38
     scanned
    0.38
     translating
    0.38
    <em>
    0.38
    Activations Density 0.015%

    No Known Activations