© 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. 40-GEMMASCOPE-2-RES-262K
    7. 219995
    Prev
    Next
    INDEX
    Explanations

    specific descriptive words

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    grayscale
    0.43
    directives
    0.42
    disposing
    0.42
    kirche
    0.40
     noncommutative
    0.40
    waypoints
    0.39
     ფედერ
    0.39
     coerc
    0.39
    ⺆
    0.39
    DUN
    0.38
    POSITIVE LOGITS
     expiry
    0.42
     expiration
    0.42
     secu
    0.41
     Radio
    0.40
     Aroma
    0.40
     Titan
    0.40
    akespe
    0.39
     records
    0.39
     Et
    0.39
     Wall
    0.39
    Activations Density 0.400%

    No Known Activations