© 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. 40-GEMMASCOPE-2-RES-262K
    7. 15550
    Prev
    Next
    INDEX
    Explanations

    multi-script words

    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_40_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
    <end_of_turn>
    0.42
     дополнительных
    0.42
    不仅
    0.41
     NSUTF
    0.40
    嫻
    0.40
    祺
    0.39
    GOND
    0.39
    MIX
    0.39
     січня
    0.39
    TOK
    0.39
    POSITIVE LOGITS
     ใคร
    0.43
     ਪ੍ਰ
    0.40
    Mel
    0.36
    道德
    0.35
     इत्यादी
    0.35
     가지고
    0.35
    Recommended
    0.35
    letown
    0.34
    ຕ
    0.34
    Waar
    0.34
    Activations Density 1.765%

    No Known Activations