© 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. 98977
    Prev
    Next
    INDEX
    Explanations

    believed to or by

    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
     zijn
    -2.61
    鷓
    -2.53
     ४
    -2.44
    ⢓
    -2.38
    ﮕ
    -2.36
    ⮜
    -2.34
    騷
    -2.30
    闔
    -2.28
    几十
    -2.23
     tesis
    -2.17
    POSITIVE LOGITS
    '
    3.48
     believed
    3.08
    .
    3.02
    of
    2.64
     Their
    2.61
    s
    2.59
     adicionar
    2.55
    ل
    2.47
    ness
    2.47
     endereco
    2.41
    Activations Density 0.003%

    No Known Activations