© 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. 17907
    Prev
    Next
    INDEX
    Explanations

    in cities

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

    data or WiFi

    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
    wort
    0.44
    ligare
    0.44
    conto
    0.44
    ustrated
    0.40
    linked
    0.40
    geme
    0.39
    zoek
    0.39
    פ
    0.39
    Ins
    0.39
    오늘은
    0.39
    POSITIVE LOGITS
     nedeniyle
    0.49
     viaj
    0.48
    assertArg
    0.48
     tedav
    0.47
     została
    0.46
     permettent
    0.46
     teşekkür
    0.45
     टूर
    0.45
     Booking
    0.44
     meriye
    0.44
    Activations Density 0.000%

    No Known Activations