© 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. 45474
    Prev
    Next
    INDEX
    Explanations

    a lot, lots, much, deal, considerably

    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
     participado
    -2.47
    蘩
    -2.44
    咵
    -2.39
    翆
    -2.33
     continúas
    -2.33
     związane
    -2.27
     gustado
    -2.25
    葙
    -2.23
     aumentado
    -2.19
    ኞ
    -2.19
    POSITIVE LOGITS
     was
    2.64
    '
    2.48
     *
    2.33
     этот
    2.31
    ”
    2.27
     είναι
    2.27
     einige
    2.23
    p
    2.22
     (>
    2.19
    )
    2.19
    Activations Density 0.009%

    No Known Activations