© 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. 13506
    Prev
    Next
    INDEX
    Explanations

    foreign language contexts

    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
    0.49
     of
    0.47
     যখন
    0.47
     *
    0.45
     if
    0.44
     in
    0.43
     measurement
    0.43
    ’
    0.42
     when
    0.42
     because
    0.42
    POSITIVE LOGITS
    ਖ
    0.46
    为此
    0.45
     цьому
    0.45
     거고
    0.44
    ราคา
    0.44
    这一切
    0.44
    इसका
    0.42
    此事
    0.42
    इसमें
    0.42
    这款
    0.41
    Activations Density 0.122%

    No Known Activations