© 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. 73348
    Prev
    Next
    INDEX
    Explanations

    Copyright notices and code metadata

    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
    fromUtf
    -0.71
     شوید
    -0.71
     Teams
    -0.71
    ksi
    -0.71
     rossi
    -0.70
    だそうです
    -0.69
     Yorkers
    -0.68
    GeneratedMessage
    -0.68
    Iranian
    -0.67
    zio
    -0.66
    POSITIVE LOGITS
    statics
    0.74
    英
    0.71
     apunta
    0.68
     Begin
    0.67
     Mako
    0.67
     concepto
    0.66
    輪
    0.65
     Sir
    0.65
    Mer
    0.65
     conceptos
    0.64
    Activations Density 0.049%

    No Known Activations