© 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-65K
    7. 3979
    Prev
    Next
    INDEX
    Explanations

    technology and software names

    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_65k_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
     носи
    0.36
     تاریخی
    0.36
    然後
    0.36
    <unused338>
    0.35
    iterranean
    0.35
    하겠습니다
    0.34
    örungen
    0.32
    󠁢
    0.32
    เท่า
    0.32
    emois
    0.31
    POSITIVE LOGITS
     경우
    0.48
    の場合は
    0.45
     esim
    0.41
    の場合
    0.41
    /
    0.41
     equivalents
    0.39
     Arcade
    0.38
     counterparts
    0.37
    における
    0.37
    RA
    0.36
    Activations Density 0.091%

    No Known Activations