© 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. 19240
    Prev
    Next
    INDEX
    Explanations

    code definitions (def, class)

    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
    
    -1.72
    ynarod
    -1.71
     canzoni
    -1.70
    seguir
    -1.67
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.66
     scena
    -1.66
    crí
    -1.64
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.63
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.62
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.60
    POSITIVE LOGITS
    y
    1.98
    t
    1.82
    !
    1.79
    k
    1.70
    }
    1.68
     “
    1.61
    *
    1.59
     [
    1.58
     have
    1.55
    ?
    1.55
    Activations Density 0.004%

    No Known Activations