© 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. 28487
    Prev
    Next
    INDEX
    Explanations

    acronyms, AI, and specific names

    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
    I
    0.58
    lib
    0.54
    {
    0.53
    (
    0.53
    where
    0.50
    ds
    0.49
    ;
    0.49
    J
    0.49
    （
    0.48
    L
    0.47
    POSITIVE LOGITS
     ഇൻ
    0.48
     ट
    0.48
     Chávez
    0.47
     કુલ
    0.45
     സമയ
    0.45
     FAA
    0.45
     EEOC
    0.44
     आज
    0.43
     এসএসসি
    0.43
     повы
    0.43
    Activations Density 0.001%

    No Known Activations