© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 38642
    Prev
    Next
    INDEX
    Explanations

    Brown

    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
    lere
    2.16
    deki
    2.09
    lerine
    2.06
    ut
    2.05
    czy
    2.03
    lä
    2.03
    lished
    1.99
    ം
    1.99
    า
    1.98
    ciones
    1.96
    POSITIVE LOGITS
     불구하고
    2.25
     tenets
    1.70
    speople
    1.68
     cannabinoids
    1.68
    াইজ
    1.64
     sarcom
    1.64
     Peas
    1.62
     vines
    1.61
     dialects
    1.61
     aberrations
    1.61
    Activations Density 0.001%

    No Known Activations