© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 90185
    Prev
    Next
    INDEX
    Explanations

    register addresses and types

    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
    籬
    -0.75
     Only
    -0.71
     песня
    -0.69
    红包
    -0.68
    樁
    -0.67
     fallen
    -0.67
    vní
    -0.67
    簒
    -0.66
    跚
    -0.66
    loth
    -0.66
    POSITIVE LOGITS
    Fern
    0.74
     bases
    0.73
    PORT
    0.73
     inflam
    0.73
    bases
    0.73
    Port
    0.72
    zeugt
    0.71
     отель
    0.71
    Pat
    0.70
    ABS
    0.69
    Activations Density 0.017%

    No Known Activations