© 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. 22-GEMMASCOPE-RES-131K
    7. 127944
    Prev
    Next
    INDEX
    Explanations

    Establishments and facilities

    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_22/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
    P
    -2.23
    A
    -2.16
    D
    -1.95
    s
    -1.93
    G
    -1.89
    es
    -1.85
    N
    -1.84
     this
    -1.83
    F
    -1.82
    T
    -1.80
    POSITIVE LOGITS
    がありますが
    1.79
    Waga
    1.78
    があり
    1.74
    Tahun
    1.72
    ᕮ
    1.63
     rosas
    1.62
    桫
    1.59
    があります
    1.58
    Rumah
    1.58
     唯美
    1.56
    Activations Density 0.085%

    No Known Activations