© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 62057
    Prev
    Next
    INDEX
    Explanations

    Starfield, Bethesda, Lockheed Martin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bronze
    0.42
     Bron
    0.39
     Bian
    0.38
    𝓭
    0.37
    द्योगिकी
    0.37
    igui
    0.37
    江
    0.36
    MY
    0.35
    alabel
    0.35
     सोम
    0.35
    POSITIVE LOGITS
     Bethesda
    0.55
    hesda
    0.46
     Const
    0.46
     bet
    0.42
    const
    0.41
    Const
    0.40
    Bet
    0.40
     Game
    0.40
     Lockheed
    0.39
    挟
    0.39
    Activations Density 0.002%

    No Known Activations