© 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. 16991
    Prev
    Next
    INDEX
    Explanations

    instruction or description

    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
    ร์
    0.42
    indungi
    0.40
    ちょっと
    0.38
     বেশিরভাগ
    0.37
    िर
    0.37
     amps
    0.37
    dimensioni
    0.36
    5
    0.36
    長
    0.35
    遌
    0.35
    POSITIVE LOGITS
     to
    0.52
     να
    0.47
    ที่จะ
    0.47
     để
    0.44
    នៃការ
    0.43
     bhith
    0.42
     تطوير
    0.41
    เพื่อให้
    0.41
     kwest
    0.40
     upang
    0.40
    Activations Density 0.071%

    No Known Activations