© 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. 28356
    Prev
    Next
    INDEX
    Explanations

    sworn to protect

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

    lists or descriptions

    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
    organisms
    0.50
    на
    0.47
    m
    0.47
     Gewerks
    0.45
    sud
    0.45
     구성
    0.44
    mass
    0.44
    ne
    0.43
    ocarpus
    0.43
    composer
    0.43
    POSITIVE LOGITS
    ل
    0.54
    لین
    0.48
     gü
    0.48
     deterred
    0.46
     pent
    0.46
    кли
    0.45
     nursing
    0.45
     multit
    0.44
     circulation
    0.43
     calculations
    0.43
    Activations Density 0.003%

    No Known Activations