© 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. 157593
    Prev
    Next
    INDEX
    Explanations

    latest spy

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

    small tube, list, rows, device WINDOW

    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
    programme
    0.48
    იღ
    0.46
     কার্যক্রম
    0.46
    سٹم
    0.46
     мәкалә
    0.45
     кампа
    0.45
     ادارے
    0.45
    𝘆
    0.44
     মোকাবে
    0.44
     Campaigns
    0.43
    POSITIVE LOGITS
    inger
    0.48
     tren
    0.45
    的标准
    0.44
    bund
    0.43
    verters
    0.43
     新
    0.43
    gave
    0.43
    istische
    0.42
    elten
    0.42
    erunner
    0.42
    Activations Density 0.001%

    No Known Activations