© 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. 6926
    Prev
    Next
    INDEX
    Explanations

    end of clause with it

    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
     the
    -2.95
    biggest
    -1.52
    飏
    -1.49
    ↔
    -1.48
    ●●
    -1.47
     Portail
    -1.45
     kebijakan
    -1.44
     Если
    -1.42
    spraak
    -1.38
     taus
    -1.38
    POSITIVE LOGITS
    .
    1.81
    してました
    1.63
     like
    1.59
    </strong>
    1.59
    しましたが
    1.55
    ̙
    1.52
    This
    1.52
    ]--;
    1.51
     Erfolgs
    1.50
     would
    1.49
    Activations Density 0.025%

    No Known Activations