© 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. 65790
    Prev
    Next
    INDEX
    Explanations

    card games and mahjong

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

    nimble enough, exploit them

    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
    }=
    0.51
    ле
    0.45
    нак
    0.45
    ATION
    0.44
    ()==
    0.44
    ச்சியை
    0.43
    르
    0.43
    ллер
    0.43
     нео
    0.42
    춘
    0.42
    POSITIVE LOGITS
     Ouais
    0.58
     Westminster
    0.47
     recounted
    0.47
     सबूत
    0.46
     Gruy
    0.46
     Burroughs
    0.46
     Honorary
    0.45
     Câmara
    0.45
     Duy
    0.45
     agreed
    0.45
    Activations Density 0.001%

    No Known Activations