© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 42974
    Prev
    Next
    INDEX
    Explanations

    TDD, Watson, Electrospinning, Scrolls

    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
    t
    2.03
    vede
    1.64
     thiểu
    1.55
    selves
    1.53
     Aiden
    1.53
     ★★
    1.52
     fhe
    1.52
    gifts
    1.52
    sellers
    1.48
     Maritime
    1.45
    POSITIVE LOGITS
     étab
    1.68
    بي
    1.65
    ка
    1.60
     destiné
    1.52
    त्मक
    1.51
    אם
    1.50
    ड
    1.43
    й
    1.42
    న్న
    1.40
    க்கு
    1.39
    Activations Density 0.001%

    No Known Activations