© 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. 30096
    Prev
    Next
    INDEX
    Explanations

    points in standings

    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
    čenje
    -0.75
     gratuitamente
    -0.72
    社長
    -0.70
     testCase
    -0.70
     바
    -0.69
    déric
    -0.68
    atelier
    -0.68
    ensuremath
    -0.67
    ᱐
    -0.66
    ougars
    -0.66
    POSITIVE LOGITS
     points
    1.97
    points
    1.44
     point
    1.39
    Points
    1.37
     Points
    1.37
     puntos
    1.29
    point
    1.20
    POINTS
    1.20
     POINTS
    1.20
     pts
    1.15
    Activations Density 0.006%

    No Known Activations