© 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. 79012
    Prev
    Next
    INDEX
    Explanations

    registered to vote, UKIP, addresses, job listings

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

    attributes, Resin, reservations, logic, LED

    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
    بیداری
    0.43
     cellul
    0.42
     lũ
    0.41
     bosonic
    0.40
    وی
    0.39
    mà
    0.39
    지
    0.39
     contraction
    0.39
    墩
    0.39
    jskiego
    0.39
    POSITIVE LOGITS
     أش
    0.52
    Adr
    0.50
    র
    0.49
     أح
    0.48
     थोड़ी
    0.47
     جميل
    0.47
     أت
    0.47
     Humanos
    0.46
     ot
    0.46
    Austral
    0.46
    Activations Density 0.000%

    No Known Activations