© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 79775
    Prev
    Next
    INDEX
    Explanations

    numbers and specific terms

    np_acts-logits-general · gemini-2.5-flash-lite

    historical periods or based on historical records

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    コア
    0.50
     forge
    0.47
     grotesque
    0.47
     Tuple
    0.47
     cookware
    0.44
     large
    0.44
     tuples
    0.44
    <0xE3>
    0.44
    Forge
    0.44
     вышла
    0.43
    POSITIVE LOGITS
    perturbed
    0.51
    agger
    0.50
    acking
    0.50
    aba
    0.49
    antile
    0.49
    acio
    0.49
    istungs
    0.49
    ibet
    0.49
    १८६
    0.48
    CreateWindow
    0.47
    Activations Density 0.000%

    No Known Activations