© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32300
    Prev
    Next
    INDEX
    Explanations

    fullscreen behavior

    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
    볍
    -0.81
    yente
    -0.77
     repealed
    -0.76
    brida
    -0.74
    voet
    -0.73
    ebra
    -0.69
     municipale
    -0.69
    rö
    -0.69
    zura
    -0.69
    idens
    -0.69
    POSITIVE LOGITS
     full
    4.31
     fullscreen
    3.70
     Full
    3.39
    full
    3.25
    fullscreen
    3.22
    Full
    3.16
    FullScreen
    3.08
    Fullscreen
    2.91
    FULL
    2.83
     FULL
    2.72
    Activations Density 0.073%

    No Known Activations