© 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. 40155
    Prev
    Next
    INDEX
    Explanations

    mathematical context and equations

    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
     atividade
    -1.09
     utilização
    -1.06
     ventanas
    -1.06
    assable
    -1.05
     červen
    -1.04
    颏
    -1.02
     entidade
    -1.02
     konkrete
    -1.00
     colocando
    -1.00
     capitulo
    -0.99
    POSITIVE LOGITS
     if
    0.97
     Whyte
    0.96
    first
    0.94
     new
    0.94
     bądź
    0.93
    p
    0.92
    just
    0.92
    sec
    0.90
    صفات
    0.90
     with
    0.90
    Activations Density 0.017%

    No Known Activations