© 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. 68698
    Prev
    Next
    INDEX
    Explanations

    range of options

    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
    Negative Logits
     tratados
    -1.63
    ?”
    -1.59
    曏
    -1.57
    ிய
    -1.56
    "}}
    -1.48
     procedura
    -1.48
     живет
    -1.45
     piernas
    -1.41
     ''}
    -1.41
     vasos
    -1.40
    POSITIVE LOGITS
     range
    2.33
     of
    2.20
    p
    1.97
    z
    1.93
     is
    1.91
    m
    1.82
    c
    1.63
    range
    1.63
    e
    1.62
    d
    1.60
    Activations Density 0.088%

    No Known Activations