© 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. 206234
    Prev
    Next
    INDEX
    Explanations

    commercial grade, free alternatives, dust free

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

    Suggests if desired ICE

    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
     regulatory
    0.51
     Quote
    0.49
     seasoning
    0.47
     צ
    0.47
     penthouse
    0.47
     kingdom
    0.46
     مل
    0.46
     luk
    0.45
    kaan
    0.45
     kon
    0.44
    POSITIVE LOGITS
    дів
    0.47
    얇
    0.46
    ிழ
    0.45
     futuras
    0.45
    hattim
    0.45
    撣
    0.44
    ПК
    0.43
    दाना
    0.43
     baseHP
    0.43
    겉
    0.43
    Activations Density 0.001%

    No Known Activations