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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69459
    Prev
    Next
    INDEX
    Explanations

    understanding and identifying knowledge

    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
     your
    -1.68
     minden
    -1.44
     each
    -1.38
     longues
    -1.34
     Дмитрий
    -1.31
     infección
    -1.30
     خریدار
    -1.27
    ınıza
    -1.23
     oude
    -1.23
     '../../../
    -1.23
    POSITIVE LOGITS
     diversa
    1.52
     how
    1.48
     that
    1.48
     oraș
    1.43
     servici
    1.38
     כוס
    1.37
    Currently
    1.30
     împre
    1.29
    Tarifs
    1.27
     commercio
    1.25
    Activations Density 0.332%

    No Known Activations