© 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. 26078
    Prev
    Next
    INDEX
    Explanations

    Hey

    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
    و
    0.78
    다
    0.68
    ാ
    0.67
     or
    0.61
    ে
    0.59
     These
    0.59
    ar
    0.55
    форма
    0.54
    ه
    0.54
     V
    0.54
    POSITIVE LOGITS
    Hey
    0.75
     hey
    0.67
    hey
    0.65
    nd
    0.57
     прия
    0.55
     måde
    0.52
     स्थापित
    0.52
     способ
    0.51
    way
    0.50
    mp
    0.50
    Activations Density 0.007%

    No Known Activations