© 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. 225840
    Prev
    Next
    INDEX
    Explanations

    link on

    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
     উপকূল
    0.61
    యర్
    0.52
    肆章
    0.51
    များကို
    0.47
     Unless
    0.46
     Cambrian
    0.46
    鿷
    0.46
     MacArthur
    0.46
    льність
    0.46
     Makarna
    0.46
    POSITIVE LOGITS
    кон
    0.44
    ou
    0.44
     OU
    0.43
    estand
    0.43
    مس
    0.43
    पे
    0.42
    ifty
    0.42
    م
    0.42
     griech
    0.41
    m
    0.41
    Activations Density 0.000%

    No Known Activations