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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 3134
    Prev
    Next
    INDEX
    Explanations

    redwood tree, oyster shell, elder berries

    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
     for
    0.73
     includes
    0.70
     has
    0.68
     is
    0.66
     ist
    0.65
    い
    0.64
     to
    0.60
     as
    0.60
     zis
    0.60
     especiales
    0.59
    POSITIVE LOGITS
    tól
    0.79
    <0x80>
    0.78
    Авто
    0.77
    tarif
    0.76
    Ис
    0.72
    Ма
    0.71
    ა
    0.71
    sponge
    0.69
    тна
    0.68
    carta
    0.68
    Activations Density 1.821%

    No Known Activations