© 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. 296
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
     will
    -1.77
    .
    -1.32
    as
    -1.31
     sottile
    -1.27
    We
    -1.24
    $.
    -1.23
    It
    -1.21
     These
    -1.20
    mathrm
    -1.20
     mètres
    -1.19
    POSITIVE LOGITS
    𐀀
    1.66
     francia
    1.45
    цыі
    1.44
    katapos
    1.43
     procé
    1.38
     glimmer
    1.37
    zten
    1.34
    どのような
    1.33
    mvh
    1.30
    榉
    1.30
    Activations Density 0.002%

    No Known Activations