© 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. 130939
    Prev
    Next
    INDEX
    Explanations

    short, from, Smooth, Dual

    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
     desglose
    -1.61
     boletín
    -1.48
    dibujos
    -1.45
     hogares
    -1.45
    äsentation
    -1.45
    Different
    -1.44
     decoracion
    -1.42
    Mereka
    -1.41
    куртка
    -1.41
    谆
    -1.41
    POSITIVE LOGITS
     your
    1.66
     any
    1.54
     all
    1.52
     the
    1.38
     my
    1.38
     golpe
    1.33
    ляется
    1.31
     serta
    1.23
     offer
    1.22
    шер
    1.22
    Activations Density 0.026%

    No Known Activations