© 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. 79198
    Prev
    Next
    INDEX
    Explanations

    CREATE TABLE IF NOT EXISTS

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ✝
    -0.84
    ceae
    -0.84
    צים
    -0.82
    hellip
    -0.82
    orghini
    -0.78
     pinos
    -0.77
    🕸
    -0.77
     pove
    -0.76
     roba
    -0.76
     Hạ
    -0.75
    POSITIVE LOGITS
    া
    0.74
    Post
    0.70
     abroad
    0.68
    Sectors
    0.66
    дня
    0.65
     fi
    0.61
    limits
    0.60
     Post
    0.59
    irled
    0.59
     C
    0.59
    Activations Density 0.065%

    No Known Activations