© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30991
    Prev
    Next
    INDEX
    Explanations

    common phrases and beginnings

    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
    ایناق
    -0.87
     ilustracji
    -0.83
    ország
    -0.82
    Distribuzione
    -0.82
     jaar
    -0.82
    attamento
    -0.77
     dobrý
    -0.77
     BAKER
    -0.77
    tomo
    -0.76
     quedaron
    -0.76
    POSITIVE LOGITS
     device
    1.40
     devices
    1.11
     transform
    1.08
    criterion
    1.01
     use
    0.93
    device
    0.91
     Device
    0.89
    ↵↵
    0.89
     model
    0.87
     transformations
    0.85
    Activations Density 0.003%

    No Known Activations