© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 9309
    Prev
    Next
    INDEX
    Explanations

    AI's Programming/Purpose

    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
    Negative Logits
     их
    0.37
     complicate
    0.36
    이야
    0.36
    Form
    0.34
    看起来
    0.34
     نخست
    0.34
    em
    0.33
    他们的
    0.33
    ík
    0.33
    이라고
    0.33
    POSITIVE LOGITS
     cannot
    0.45
    旨在
    0.45
     renforc
    0.40
     unable
    0.40
     powerless
    0.40
     bertujuan
    0.40
     couldn
    0.39
     checked
    0.39
     strives
    0.38
     actively
    0.38
    Activations Density 0.229%

    No Known Activations