© 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. 84087
    Prev
    Next
    INDEX
    Explanations

    2 followed by d/2, Q:, A double, Rosewood

    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
    recipients
    -0.77
     recipients
    -0.77
    Recipients
    -0.76
     cornerback
    -0.75
    ács
    -0.73
    LISA
    -0.72
    Rainer
    -0.71
     bacterio
    -0.71
    thiet
    -0.71
    Zem
    -0.70
    POSITIVE LOGITS
    aly
    0.84
    %@
    0.84
    orer
    0.79
     Pali
    0.79
    iche
    0.79
    idic
    0.77
    olg
    0.77
    fet
    0.76
     Metallic
    0.75
     quæ
    0.75
    Activations Density 0.004%

    No Known Activations