© 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. 22-GEMMASCOPE-RES-131K
    7. 66433
    Prev
    Next
    INDEX
    Explanations

    daily timings

    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_22/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
     mascarilla
    -1.42
     enorme
    -1.37
    回到了
    -1.30
    Bahan
    -1.23
    Вот
    -1.21
     esportes
    -1.21
     that
    -1.20
     cadeiras
    -1.19
     óculos
    -1.18
     cinto
    -1.17
    POSITIVE LOGITS
     or
    1.73
     your
    1.63
     until
    1.44
     by
    1.35
    岀
    1.33
     ১
    1.30
     рекомен
    1.23
     before
    1.23
     during
    1.22
    啖
    1.22
    Activations Density 0.012%

    No Known Activations