© 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. 75958
    Prev
    Next
    INDEX
    Explanations

    motherboards and computer cases

    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
     אתה
    -0.84
    rollment
    -0.74
     hinzu
    -0.73
    ggior
    -0.71
     unidad
    -0.69
    Nielsen
    -0.68
    unidad
    -0.68
     monnaie
    -0.68
    shed
    -0.67
     popis
    -0.67
    POSITIVE LOGITS
     motherboard
    2.25
     board
    2.02
     mother
    1.95
     boards
    1.88
    mother
    1.71
    board
    1.69
    Mother
    1.67
     Mother
    1.58
    boards
    1.55
    BOARD
    1.47
    Activations Density 0.056%

    No Known Activations