© 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. 22-GEMMASCOPE-RES-131K
    7. 16402
    Prev
    Next
    INDEX
    Explanations

    discard mode

    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_22/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
     metaphysics
    -0.92
     تغذ
    -0.85
    袜
    -0.85
    uš
    -0.84
    &:
    -0.81
    為に
    -0.79
     jane
    -0.78
     لإ
    -0.78
    eficent
    -0.78
    上了
    -0.77
    POSITIVE LOGITS
     choix
    1.09
     enum
    1.07
     choice
    0.99
     choices
    0.98
    Soorten
    0.96
    Enum
    0.95
     among
    0.93
     options
    0.90
     choose
    0.90
    choice
    0.89
    Activations Density 0.006%

    No Known Activations