© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 35084
    Prev
    Next
    INDEX
    Explanations

    urls or domain names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avier
    1.06
    ஃப்
    1.06
    िया
    1.02
    giveness
    1.02
    нт
    1.01
    에서는
    0.99
    wunsch
    0.97
    ف
    0.97
     worksheets
    0.93
    angebot
    0.93
    POSITIVE LOGITS
     Controvers
    1.09
     of
    1.07
     L
    1.05
     Controversy
    1.00
     hegemony
    0.99
     timid
    0.96
     Poet
    0.94
    ्‍यादा
    0.93
     наук
    0.93
    ل
    0.92
    Activations Density 0.015%

    No Known Activations