© 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. 193797
    Prev
    Next
    INDEX
    Explanations

    Juan de Fuca, extremely fast, with Microsoft

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

    status reports and descriptions

    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
    MSFont
    0.52
     предметов
    0.50
     স্বতন্ত্র
    0.49
     おはよう
    0.49
     ಪ್ರಕರಣ
    0.49
     教え
    0.49
     እ
    0.48
     अधि
    0.48
     ochrony
    0.48
     〢
    0.47
    POSITIVE LOGITS
    ↵↵
    0.52
     Music
    0.45
    ويل
    0.45
    وال
    0.45
     Hoop
    0.43
    拿
    0.43
    韪
    0.43
     frees
    0.43
     judicious
    0.42
    नु
    0.41
    Activations Density 0.000%

    No Known Activations