© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79538
    Prev
    Next
    INDEX
    Explanations

    rights reserved

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     visualization
    -0.71
    游戏
    -0.71
     kumpulan
    -0.69
     Nellie
    -0.68
     Morgen
    -0.67
    Chunk
    -0.65
     collisions
    -0.65
     excessive
    -0.64
     Anexo
    -0.63
     Hartford
    -0.63
    POSITIVE LOGITS
     popoli
    0.77
    oky
    0.75
    pholes
    0.74
    잣
    0.74
    itig
    0.74
    󠁥
    0.71
    лев
    0.70
    øj
    0.70
    σουν
    0.68
     Violation
    0.68
    Activations Density 0.062%

    No Known Activations