© 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. 6568
    Prev
    Next
    INDEX
    Explanations

    modular components and systems

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

    you define or given a

    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
    👿
    0.49
     ഇക്കാര
    0.49
    Ꮏ
    0.48
     уверен
    0.48
    愈
    0.47
     됐
    0.46
    もあった
    0.46
    ございました
    0.46
    😠
    0.46
     뉴스
    0.45
    POSITIVE LOGITS
     modular
    0.71
     handheld
    0.66
    専用
    0.61
     tubular
    0.61
    modular
    0.59
     Modular
    0.59
    Modular
    0.58
     eponymous
    0.58
     modules
    0.57
     pomocí
    0.57
    Activations Density 0.113%

    No Known Activations