© 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. 86508
    Prev
    Next
    INDEX
    Explanations

    scores on or higher

    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
    ”:
    -1.47
     ajouter
    -1.38
     pieds
    -1.38
     effek
    -1.38
     alent
    -1.37
    ěř
    -1.34
     fleurs
    -1.34
     ceux
    -1.34
     peines
    -1.32
     remercier
    -1.30
    POSITIVE LOGITS
     on
    1.62
     Unglück
    1.52
     Sünden
    1.45
     Empfindung
    1.45
     Gefühle
    1.37
     Entste
    1.32
     murió
    1.32
     apareció
    1.32
     Vergangenheit
    1.30
     Sehingga
    1.30
    Activations Density 0.030%

    No Known Activations