© 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. 45404
    Prev
    Next
    INDEX
    Explanations

    non-English words and code tokens

    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
    on
    -1.16
     berühm
    -1.15
     множество
    -1.13
     many
    -1.12
     nosso
    -1.08
     but
    -1.08
    </u>
    -1.07
     включая
    -1.07
    HORIZONTAL
    -1.06
    CROSSTALK
    -1.06
    POSITIVE LOGITS
    proteins
    1.23
     kuitenkin
    1.20
    Jahre
    1.20
     alſo
    1.19
     fernández
    1.18
    𓆏
    1.18
     problemen
    1.17
     också
    1.17
     Svensson
    1.17
     problemer
    1.16
    Activations Density 0.010%

    No Known Activations