© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44729
    Prev
    Next
    INDEX
    Explanations

    percentages and variations

    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
     particolarmente
    -1.59
     destinés
    -1.38
    怵
    -1.38
     vår
    -1.34
    ︲
    -1.30
     was
    -1.29
    了下
    -1.27
     uffic
    -1.26
     dışında
    -1.26
     durumu
    -1.24
    POSITIVE LOGITS
     even
    1.66
     one
    1.63
     when
    1.59
     in
    1.47
    ซ์
    1.44
     although
    1.38
    gunakan
    1.33
     ciclista
    1.32
     ensuring
    1.27
     одна
    1.27
    Activations Density 0.058%

    No Known Activations