© 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. 3549
    Prev
    Next
    INDEX
    Explanations

    positive evaluation

    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
    vább
    -1.60
    ícias
    -1.43
    vaila
    -1.43
    ortic
    -1.38
    strual
    -1.37
    itively
    -1.33
    lihood
    -1.33
    giver
    -1.32
    givers
    -1.32
     ***!
    -1.31
    POSITIVE LOGITS
     great
    3.39
     good
    3.13
     excellent
    2.53
     nice
    2.28
     lots
    2.27
     friendly
    2.05
     very
    1.89
     beautiful
    1.88
     well
    1.79
     decent
    1.77
    Activations Density 0.014%

    No Known Activations