© 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. 72326
    Prev
    Next
    INDEX
    Explanations

    disfavored

    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
    嵛
    -2.48
     climático
    -2.31
    今後も
    -2.31
    
    -2.31
     barata
    -2.30
     tornar
    -2.27
    莇
    -2.27
    氿
    -2.19
     Fällen
    -2.17
     zahlreiche
    -2.17
    POSITIVE LOGITS
    e
    3.02
    }
    2.77
    ",
    2.72
    2.53
    3
    2.53
    for
    2.39
    u
    2.31
    </
    2.28
     für
    2.27
    X
    2.25
    Activations Density 0.028%

    No Known Activations