© 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. 25513
    Prev
    Next
    INDEX
    Explanations

    universe expansion

    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
    ปฏิ
    0.44
    GMO
    0.44
     অভিব
    0.43
    竇
    0.43
     совпада
    0.42
    AI
    0.42
    fragen
    0.42
     protest
    0.42
     பேராசிரியர்
    0.42
    ραγ
    0.41
    POSITIVE LOGITS
    <0x0D>
    0.50
     successors
    0.50
     টাইগার
    0.48
    Its
    0.47
     שהוא
    0.46
    Each
    0.46
    телите
    0.45
     ocean
    0.45
    نك
    0.43
    Tiger
    0.43
    Activations Density 0.001%

    No Known Activations