© 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. 98741
    Prev
    Next
    INDEX
    Explanations

    0 followed by punctuation

    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
     NOT
    -1.59
    стана
    -1.56
     filmen
    -1.51
     ſome
    -1.47
     zove
    -1.40
     десять
    -1.40
     puncak
    -1.38
    SOME
    -1.37
    臜
    -1.36
    裢
    -1.35
    POSITIVE LOGITS
     nachher
    1.52
    genheiten
    1.46
    gencias
    1.46
    tividade
    1.34
     beneficiario
    1.32
     because
    1.30
     więc
    1.26
     except
    1.26
     until
    1.26
     since
    1.25
    Activations Density 0.117%

    No Known Activations