© 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. 10-GEMMASCOPE-RES-131K
    7. 68419
    Prev
    Next
    INDEX
    Explanations

    credit score and rating

    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_10/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
    ⩕
    -1.63
     hoffe
    -1.59
    TintMode
    -1.58
     COMERC
    -1.56
    onymous
    -1.52
    MLLoader
    -1.52
    不舒服
    -1.51
     bagus
    -1.50
    irical
    -1.47
    iibo
    -1.45
    POSITIVE LOGITS
    鱟
    1.73
    ada
    1.72
    ஂ
    1.61
     
    1.49
    _
    1.47
     colorear
    1.45
     enchanting
    1.45
    J
    1.45
     coworkers
    1.42
     típica
    1.42
    Activations Density 0.004%

    No Known Activations