© 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. 12712
    Prev
    Next
    INDEX
    Explanations

    lists ending with colons or periods

    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
     affectionate
    0.49
    shareButton
    0.48
    紶
    0.48
    嵃
    0.48
     ravaged
    0.47
    󰀄
    0.47
    vorm
    0.46
     продолжаем
    0.46
    இந்திய
    0.46
     էր
    0.46
    POSITIVE LOGITS
     S
    0.57
     I
    0.50
      
    0.49
     s
    0.47
     (
    0.46
     even
    0.45
     Pre
    0.45
     to
    0.45
     -
    0.44
     A
    0.43
    Activations Density 0.002%

    No Known Activations