© 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. 10922
    Prev
    Next
    INDEX
    Explanations

    government and health institutions

    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
    ześnie
    1.13
     वसूल
    1.12
     empresarial
    1.06
    ijske
    1.06
     revolutionaries
    1.05
     deltaTime
    1.05
    嫨
    1.05
     anxiously
    1.04
     innebär
    1.03
     Där
    1.03
    POSITIVE LOGITS
    ти
    1.40
    ten
    1.34
    ль
    1.22
    ts
    1.09
    ta
    1.09
    ments
    1.02
    irs
    1.02
    7
    1.02
    ressed
    1.01
    ting
    1.00
    Activations Density 0.038%

    No Known Activations