© 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. 1353
    Prev
    Next
    INDEX
    Explanations

    recipe and ingredient lists

    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
    u
    1.36
    is
    1.30
    at
    1.00
    uose
    0.96
    իկ
    0.96
    ↵↵
    0.94
    os
    0.91
    er
    0.89
    are
    0.89
     Sharp
    0.88
    POSITIVE LOGITS
    Ingredients
    1.39
    ну
    1.35
     ingred
    1.22
     ingrédients
    1.18
     milliliters
    1.14
     acyl
    1.13
     concealer
    1.13
     vinaig
    1.11
    陉
    1.10
     recette
    1.09
    Activations Density 0.168%

    No Known Activations