© 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. 41146
    Prev
    Next
    INDEX
    Explanations

    nationalities and countries

    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
    on
    1.02
    in
    0.99
    he
    0.98
    or
    0.95
    it
    0.90
    ed
    0.90
    of
    0.90
    ě
    0.89
    ally
    0.87
    etic
    0.87
    POSITIVE LOGITS
     aviones
    0.99
    marshalO
    0.95
     incumpl
    0.95
     serían
    0.94
     financieros
    0.91
     lawmaker
    0.91
     avión
    0.90
     llamados
    0.89
     Наталья
    0.89
     giáo
    0.88
    Activations Density 0.027%

    No Known Activations