© 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. 212810
    Prev
    Next
    INDEX
    Explanations

    specialization sports

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

    break system packages

    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
    lebih
    0.44
     hopeful
    0.43
    -;
    0.41
    :\
    0.41
    hia
    0.40
     brighter
    0.39
     impegno
    0.39
    tev
    0.39
    hae
    0.39
    hapi
    0.39
    POSITIVE LOGITS
     Германия
    0.57
    시스템
    0.52
     система
    0.51
    에도
    0.49
     Togo
    0.49
    닫
    0.49
     systèmes
    0.48
    ◑
    0.48
     Германии
    0.48
    ﻖ
    0.48
    Activations Density 0.000%

    No Known Activations