Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 12045
    Prev
    Next
    INDEX
    Explanations

    academic and technical concepts

    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
    ,
    0.46
    дой
    0.45
    вок
    0.45
    4
    0.43
    送
    0.43
     decentral
    0.42
     avoids
    0.42
     embarrass
    0.42
     seep
    0.42
     inbox
    0.41
    POSITIVE LOGITS
     ഗവേഷ
    0.59
     શિક્ષણ
    0.52
     ተጨማሪ
    0.52
     المزيد
    0.51
    ㈤
    0.49
     بیشتر
    0.47
     பகுதி
    0.47
     لگاتا
    0.47
     πολι
    0.47
     જન્મ
    0.46
    Activations Density 0.000%

    No Known Activations