© 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. 172308
    Prev
    Next
    INDEX
    Explanations

    colorful photos, comprehensive guide

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

    Steganography, cryptography, map, visualizing

    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
    麃
    0.51
    蕪
    0.50
    觴
    0.48
    鬯
    0.47
    Celltype
    0.47
    ytu
    0.46
     colt
    0.45
    нару
    0.45
    舛
    0.45
     Delft
    0.45
    POSITIVE LOGITS
    m
    0.50
    l
    0.47
     remain
    0.47
    -
    0.47
    iid
    0.47
     rotates
    0.46
    i
    0.45
     averages
    0.43
     dinners
    0.43
     exchanges
    0.42
    Activations Density 0.000%

    No Known Activations