© 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-65K
    7. 61225
    Prev
    Next
    INDEX
    Explanations

    generally open fusion choice red sun

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ulous
    0.46
    areas
    0.44
     ambientales
    0.42
    विड़
    0.42
    apsack
    0.42
    asks
    0.42
    ;',
    0.41
    habitants
    0.41
     spaces
    0.39
    '];
    0.39
    POSITIVE LOGITS
    до
    0.52
    enian
    0.48
    এটা
    0.45
    AR
    0.44
     Tena
    0.44
    RH
    0.43
    RE
    0.43
    대한
    0.42
     sprinter
    0.41
    OLINA
    0.41
    Activations Density 0.003%

    No Known Activations