© 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. 1334
    Prev
    Next
    INDEX
    Explanations

    `.byte` and numbers

    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
     of
    -1.84
     verde
    -1.52
     —
    -1.52
     în
    -1.52
     enorm
    -1.50
    ‗
    -1.48
     mee
    -1.48
     inge
    -1.43
     pentru
    -1.41
    ското
    -1.41
    POSITIVE LOGITS
     when
    2.09
     двох
    1.91
     many
    1.89
     two
    1.77
     while
    1.69
     навіть
    1.66
     several
    1.64
     there
    1.63
     even
    1.57
    って言
    1.56
    Activations Density 0.051%

    No Known Activations