© 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. 100930
    Prev
    Next
    INDEX
    Explanations

    time and location

    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
    r
    0.57
    lub
    0.47
    t
    0.46
    isph
    0.44
    '
    0.43
    iges
    0.41
    _
    0.40
    rrr
    0.39
    dfs
    0.39
    myp
    0.38
    POSITIVE LOGITS
     ἢ
    0.52
     സമയം
    0.49
    മ്പോ
    0.48
     हुई
    0.47
     স
    0.46
     ವೇಳ
    0.46
     sechs
    0.46
     தொலைக்கா
    0.46
    ゼ
    0.45
     telev
    0.45
    Activations Density 0.001%

    No Known Activations