© 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. 15743
    Prev
    Next
    INDEX
    Explanations

    fillers and web references

    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
     mostró
    -1.62
     the
    -1.53
     it
    -1.52
     postures
    -1.41
     permitió
    -1.39
    ној
    -1.32
     обычно
    -1.23
    Sementara
    -1.22
    aculture
    -1.22
    Untuk
    -1.22
    POSITIVE LOGITS
    </h2>
    1.86
    )−
    1.34
    __":
    1.34
    styleUrls
    1.32
     diras
    1.31
    currency
    1.29
    tt
    1.29
     itinéraires
    1.28
    "
    1.25
    the
    1.23
    Activations Density 0.014%

    No Known Activations