© 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. 113922
    Prev
    Next
    INDEX
    Explanations

    the cycle

    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
    skjaer
    -1.67
    ’
    -1.66
     gestartet
    -1.59
    ühner
    -1.59
    泚
    -1.48
    rogels
    -1.45
     \
    -1.45
     acolo
    -1.45
    medriver
    -1.40
    嚓
    -1.37
    POSITIVE LOGITS
     bidra
    1.76
    蹰
    1.73
    其他
    1.59
    Beskrivning
    1.52
     també
    1.49
     nasıl
    1.48
     ricos
    1.47
     problemet
    1.47
    他の
    1.46
    Beskrivelse
    1.46
    Activations Density 0.022%

    No Known Activations