© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66803
    Prev
    Next
    INDEX
    Explanations

    bother to and time phrases

    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
     bienvenue
    -1.61
     récompense
    -1.52
     negras
    -1.45
     saisie
    -1.43
     FINALLY
    -1.41
     jsi
    -1.41
    スムーズ
    -1.40
    たまたま
    -1.40
     feront
    -1.40
     célé
    -1.40
    POSITIVE LOGITS
    after
    1.45
     How
    1.38
    ziek
    1.38
     in
    1.35
     bother
    1.34
    ITY
    1.34
     You
    1.34
    ленной
    1.30
    </strong>
    1.30
    ION
    1.28
    Activations Density 0.011%

    No Known Activations