© 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. 53808
    Prev
    Next
    INDEX
    Explanations

    participation and candidacy

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

    esports, competition, finance, legal, and candidatures

    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
     they
    0.44
     Simone
    0.43
    *
    0.43
    ha
    0.43
    الا
    0.42
     বোর্ড
    0.40
    بق
    0.40
     former
    0.40
     hygien
    0.39
    ima
    0.38
    POSITIVE LOGITS
    参赛
    0.58
     candidature
    0.55
     अभ्यर्थी
    0.53
     distanceFrom
    0.53
    țin
    0.52
    BrI
    0.52
    郄
    0.51
     اولم
    0.50
     преди
    0.50
     notori
    0.50
    Activations Density 0.000%

    No Known Activations