© 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. 89813
    Prev
    Next
    INDEX
    Explanations

    documentation and configuration keywords

    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
    ই
    -0.84
     escolher
    -0.78
     obtiene
    -0.74
    支援
    -0.73
     alcançar
    -0.70
     enchufe
    -0.69
    ensä
    -0.69
     chond
    -0.69
     Theatres
    -0.68
    প
    -0.66
    POSITIVE LOGITS
    writeByte
    0.72
     external
    0.71
    Signing
    0.70
    ähkö
    0.69
     sprung
    0.68
     jefe
    0.68
    gher
    0.68
    omiya
    0.67
    对外
    0.67
     ${
    0.66
    Activations Density 0.064%

    No Known Activations