© 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. 251466
    Prev
    Next
    INDEX
    Explanations

    creation: , gods, casino, Monday, Interestingly

    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
    ❑
    0.49
    committee
    0.47
    াধ্য
    0.47
     TextBox
    0.46
    parsed
    0.46
    τας
    0.45
     ಸಂಧಿ
    0.45
     অতএব
    0.44
    ভিউ
    0.44
    parsing
    0.44
    POSITIVE LOGITS
    지
    0.47
     carn
    0.46
     बढ़त
    0.44
     Jackman
    0.44
    ج
    0.43
    -
    0.43
    ش
    0.43
    獲得
    0.43
     Yamazaki
    0.42
     solução
    0.42
    Activations Density 0.000%

    No Known Activations