© 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. 113915
    Prev
    Next
    INDEX
    Explanations

    Baku, plotly, SEAL BEACH

    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
     Then
    -2.80
     inocente
    -2.20
    rdı
    -2.17
    鉀
    -2.16
     gracios
    -2.09
    饹
    -2.08
     drugi
    -2.05
     woo
    -2.05
     kategori
    -2.03
    部は
    -1.99
    POSITIVE LOGITS
    an
    2.78
    i
    2.58
    ta
    2.50
    just
    2.44
    }
    2.31
    ‘
    2.27
    вгений
    2.20
    ll
    2.19
    必要な
    2.13
    C
    2.11
    Activations Density 0.007%

    No Known Activations