© 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. 161242
    Prev
    Next
    INDEX
    Explanations

    ebooks, domain, job, 'til, promised

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

    cannot run or execute code

    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
    5
    0.50
    stoffe
    0.43
    IOR
    0.43
    desi
    0.43
     ليا
    0.42
    ο
    0.41
    arei
    0.41
    莖
    0.41
    can
    0.41
    steelblue
    0.41
    POSITIVE LOGITS
     দূরে
    0.47
     hamburger
    0.45
     eprintln
    0.45
     Predator
    0.45
     bienvenidas
    0.45
     Unicorn
    0.43
    䡏
    0.43
     visitor
    0.43
    难
    0.42
    LinkClicked
    0.42
    Activations Density 0.001%

    No Known Activations