© 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. 240685
    Prev
    Next
    INDEX
    Explanations

    satisfied proud gallery Wallguard®

    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
    dak
    0.47
    reta
    0.47
    dens
    0.47
    h
    0.46
    dete
    0.45
    يال
    0.45
     कमाल
    0.44
    tails
    0.44
     use
    0.44
    t
    0.43
    POSITIVE LOGITS
     credo
    0.47
    بی
    0.46
    贯
    0.46
    开头
    0.43
     அடிப்பட
    0.42
     ifade
    0.42
     चित्रित
    0.41
     giovani
    0.41
    க்கமாக
    0.41
     सरोवर
    0.40
    Activations Density 0.001%

    No Known Activations