© 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. 86905
    Prev
    Next
    INDEX
    Explanations

    mouse wheel scrolling

    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
    AGAT
    -0.85
    xil
    -0.84
    Rif
    -0.84
     quadril
    -0.73
    PointerException
    -0.73
    äf
    -0.71
    automat
    -0.70
     Khart
    -0.68
    Testo
    -0.67
    CORN
    -0.67
    POSITIVE LOGITS
     wheel
    2.45
    wheel
    2.16
     Wheel
    1.94
    Wheel
    1.86
     WHEEL
    1.79
    WHEEL
    1.67
     scroll
    1.63
     wheels
    1.55
     scrolls
    1.30
    roller
    1.29
    Activations Density 0.028%

    No Known Activations