© 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. 12185
    Prev
    Next
    INDEX
    Explanations

    indicates absence

    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
    s
    -1.73
     of
    -1.48
     not
    -1.40
    this
    -1.28
     as
    -1.22
    k
    -1.21
    ituitary
    -1.21
     categor
    -1.20
     THIS
    -1.19
    in
    -1.18
    POSITIVE LOGITS
     erstes
    1.34
    鎂
    1.33
     fortalec
    1.32
    umum
    1.30
    ısı
    1.30
     NUEVO
    1.26
     jurí
    1.24
     kayna
    1.24
    elcome
    1.23
     römischen
    1.22
    Activations Density 0.038%

    No Known Activations