© 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. 71260
    Prev
    Next
    INDEX
    Explanations

    likely due to

    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
     изначально
    0.49
     લગભગ
    0.47
     অধীনে
    0.45
     প্যার
    0.42
     Plague
    0.42
     💪
    0.41
     טוב
    0.41
     যেখানে
    0.41
    獾
    0.41
     行
    0.41
    POSITIVE LOGITS
     frivol
    0.43
     cuidados
    0.43
    وبت
    0.43
     a
    0.43
     heartbreaking
    0.42
     motoring
    0.42
     idolat
    0.41
     stoff
    0.41
     thờ
    0.41
     naudoj
    0.40
    Activations Density 0.014%

    No Known Activations