© 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. 109699
    Prev
    Next
    INDEX
    Explanations

    legal citations and terms

    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
     condemned
    0.47
    findById
    0.46
     outweighed
    0.45
     complained
    0.44
     condemning
    0.44
     subdued
    0.42
     discredited
    0.42
    │
    0.42
     अक्टूबर
    0.42
    nienia
    0.42
    POSITIVE LOGITS
    utional
    0.53
     stimul
    0.46
     زمن
    0.44
    小学
    0.43
     stance
    0.42
     удоволь
    0.42
    Position
    0.42
    TEGER
    0.41
     ather
    0.41
    ISPW
    0.41
    Activations Density 0.001%

    No Known Activations