© 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. 16801
    Prev
    Next
    INDEX
    Explanations

    content guidelines

    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
     вообще
    0.63
     Вообще
    0.54
     еще
    0.54
    น่า
    0.52
    k
    0.51
     ещё
    0.47
    v
    0.46
    U
    0.46
    ยัง
    0.45
    d
    0.45
    POSITIVE LOGITS
     accelerates
    0.50
     controllers
    0.47
    ்கலை
    0.46
     Konzert
    0.46
     "|
    0.46
     microphones
    0.45
     dishes
    0.44
     membranes
    0.44
     waveguides
    0.43
     Dienstag
    0.42
    Activations Density 0.001%

    No Known Activations