© 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. 37246
    Prev
    Next
    INDEX
    Explanations

    going beyond just

    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
     苏
    0.47
    čan
    0.45
    Ӏо
    0.45
     企业
    0.45
    ëlle
    0.45
     Seattle
    0.44
    ż
    0.44
    拒绝
    0.43
     Jiří
    0.43
     Philadelphia
    0.43
    POSITIVE LOGITS
     auxili
    0.56
    ب
    0.54
    بع
    0.52
     encoders
    0.50
     warrants
    0.47
     artworks
    0.47
     artistas
    0.47
     admirers
    0.47
     vassals
    0.46
    ਮ
    0.46
    Activations Density 0.002%

    No Known Activations