© 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. 74053
    Prev
    Next
    INDEX
    Explanations

    piezoelectric and optical conversion

    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
    蚡
    -1.84
     vermel
    -1.65
    wwwwwwww
    -1.62
     Inſ
    -1.59
     schild
    -1.52
    €™
    -1.49
     studenten
    -1.48
    wwwww
    -1.48
     bénéficiaire
    -1.46
    farms
    -1.46
    POSITIVE LOGITS
     as
    1.63
    3
    1.53
    4
    1.41
     
    1.18
     B
    1.15
    jerc
    1.14
     like
    1.13
     S
    1.12
     Like
    1.11
    ômetro
    1.09
    Activations Density 0.087%

    No Known Activations