© 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. 172826
    Prev
    Next
    INDEX
    Explanations

    Terex Track Utility Vehicle

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

    aiogram and methodology

    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
    自身
    0.48
    точ
    0.48
     ток
    0.46
    ี
    0.46
    вил
    0.43
    真实的
    0.43
    变换
    0.42
    自身的
    0.41
    тым
    0.41
    ;
    0.41
    POSITIVE LOGITS
     Inicial
    0.51
     Vorstand
    0.50
     Einheit
    0.46
     ITEMIZED
    0.45
     Peña
    0.45
     প্রথমেই
    0.45
     inicial
    0.45
     pierwszy
    0.44
     voorz
    0.44
     Ajoutez
    0.44
    Activations Density 0.001%

    No Known Activations