© 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. 13589
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

    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
    我們
    -1.63
     quartiere
    -1.18
     Août
    -1.17
    меч
    -1.17
     atap
    -1.16
     Ogni
    -1.16
     maría
    -1.16
     ganger
    -1.15
     Harus
    -1.14
     Belajar
    -1.14
    POSITIVE LOGITS
     ancora
    1.25
     concept
    1.19
    en
    1.17
    '])
    1.16
    xFFFF
    1.14
     enough
    1.13
     había
    1.13
     erbjuder
    1.12
     on
    1.12
     can
    1.10
    Activations Density 0.070%

    No Known Activations