© 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. 34866
    Prev
    Next
    INDEX
    Explanations

    explanation depends on quality

    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
     이론
    0.48
     완성
    0.45
    절
    0.44
    열
    0.43
    이를
    0.43
     성능
    0.43
     THEORY
    0.43
    leece
    0.42
    ྥ
    0.42
     계산
    0.42
    POSITIVE LOGITS
    出席
    0.47
     rarely
    0.45
    做出
    0.44
     faulted
    0.42
    檚
    0.42
    ing
    0.42
    ems
    0.41
     singularly
    0.40
     absent
    0.40
     attends
    0.40
    Activations Density 0.002%

    No Known Activations