© 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. 71520
    Prev
    Next
    INDEX
    Explanations

    content and structure

    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
    iczne
    0.44
    要么
    0.43
     różne
    0.40
     heterod
    0.40
    -
    0.40
    िज़
    0.39
     ukon
    0.39
    -(-
    0.39
     subclasses
    0.38
     końca
    0.38
    POSITIVE LOGITS
    ushu
    0.48
    內容
    0.48
    भा
    0.46
    堈
    0.44
    КА
    0.44
    ोजन
    0.43
    Rn
    0.43
    contents
    0.42
     रंजन
    0.42
    MAE
    0.42
    Activations Density 0.007%

    No Known Activations