© 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. 254750
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Укра
    0.46
    捛
    0.46
    ())
    0.45
     поряд
    0.45
     Nahrung
    0.44
     Україн
    0.44
    ObjectHideFlags
    0.44
    ül
    0.44
     заб
    0.44
    阊
    0.43
    POSITIVE LOGITS
     prohibits
    0.46
    訴
    0.46
     mówi
    0.45
    と呼ばれる
    0.45
    ਵੇਂ
    0.44
     benefit
    0.44
    ほうが
    0.43
     특징
    0.43
     meter
    0.43
     facteur
    0.43
    Activations Density 0.000%

    No Known Activations