© 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. 24997
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    Negative Logits
    ùy
    -0.84
    טל
    -0.78
    ACCIÓN
    -0.78
    onActivityResult
    -0.75
     Heel
    -0.75
    şte
    -0.75
     परिव
    -0.75
     PROVISIONS
    -0.75
     problemet
    -0.75
     effetti
    -0.74
    POSITIVE LOGITS
     ti
    0.84
    omus
    0.76
     enough
    0.75
     ešte
    0.74
     популяр
    0.73
     gesunde
    0.72
     môžete
    0.71
     برابوك
    0.71
    érience
    0.70
    늪
    0.70
    Activations Density 0.008%

    No Known Activations