© 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. 88902
    Prev
    Next
    INDEX
    Explanations

    drive `file` recovery

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

    Coralia, similarities existed, sourced

    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
    젹
    0.53
     organize
    0.52
     ears
    0.50
     sails
    0.48
    органи
    0.47
    맇
    0.47
     elasticity
    0.46
     granola
    0.46
     effectuer
    0.46
     ރ
    0.46
    POSITIVE LOGITS
     Welt
    0.52
    Welt
    0.51
    Support
    0.48
    World
    0.48
    Pseudo
    0.47
     Pérez
    0.47
    welt
    0.46
     Unterstützung
    0.46
     Sánchez
    0.46
    support
    0.45
    Activations Density 0.002%

    No Known Activations