© 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. 1217
    Prev
    Next
    INDEX
    Explanations

    pre-post modifiers

    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
     seag
    0.36
    舉行
    0.35
     shirts
    0.35
     achter
    0.35
     tinha
    0.34
    नियां
    0.33
    音が
    0.33
     prettiest
    0.33
     ጭ
    0.33
     fur
    0.33
    POSITIVE LOGITS
     nuanced
    0.39
     perceptive
    0.39
     scalable
    0.39
     proactive
    0.38
     normative
    0.37
     methodological
    0.37
     societal
    0.36
     mechanistic
    0.36
     impactful
    0.36
     transformative
    0.36
    Activations Density 0.042%

    No Known Activations