© 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. 49227
    Prev
    Next
    INDEX
    Explanations

    file usage ownership Marcia inside

    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
     sailing
    0.46
     rehearsals
    0.46
     playback
    0.44
     nautical
    0.44
     serving
    0.43
     traveling
    0.42
     rhum
    0.41
    ش
    0.41
     orchestration
    0.40
     heightened
    0.39
    POSITIVE LOGITS
     деше
    0.54
    非法
    0.49
     अवैध
    0.42
    aarr
    0.42
     பழைய
    0.42
     போரா
    0.41
     የበለጠ
    0.41
    土地
    0.40
    ক্ষেত্র
    0.40
     accusations
    0.40
    Activations Density 0.017%

    No Known Activations