© 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. 52188
    Prev
    Next
    INDEX
    Explanations

    creative and inventive posts

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

    database errors, medieval weaponry, waves

    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
     Học
    0.49
    Solver
    0.49
    Matt
    0.48
    o
    0.48
     ước
    0.48
    teau
    0.46
     Quickly
    0.45
    GetName
    0.45
     Matt
    0.45
    hoa
    0.45
    POSITIVE LOGITS
    νομ
    0.52
    管
    0.49
     plena
    0.46
    本身
    0.45
    ❽
    0.45
    Externe
    0.45
     speriment
    0.44
    从来
    0.44
    首都
    0.44
     crisis
    0.44
    Activations Density 0.000%

    No Known Activations