© 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. 34-GEMMASCOPE-RES-131K
    7. 115503
    Prev
    Next
    INDEX
    Explanations

    structured information or data formats

    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_34/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
     сутки
    -0.85
     Bial
    -0.81
     डाल
    -0.80
     mē
    -0.74
     thích
    -0.73
    assuming
    -0.73
    distan
    -0.73
     erwartet
    -0.73
    IONE
    -0.73
     Kruger
    -0.72
    POSITIVE LOGITS
     Structure
    1.12
    Structure
    1.05
     STRUCTURE
    0.97
     Estructura
    0.95
     strukt
    0.89
     structure
    0.86
     Struct
    0.85
    structure
    0.85
     Struktur
    0.84
    MfG
    0.82
    Activations Density 0.031%

    No Known Activations