© 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
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 37866
    Prev
    Next
    INDEX
    Explanations

    creative ideas

    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
     recta
    0.83
    직
    0.80
     trabalh
    0.80
    লন
    0.80
     жі
    0.79
    矨
    0.79
     въз
    0.77
     ദു
    0.77
     ദ
    0.76
    й
    0.76
    POSITIVE LOGITS
    ering
    0.93
    />
    0.87
    in
    0.84
    z
    0.83
    shipping
    0.82
    bock
    0.81
    time
    0.80
    idaire
    0.78
    liners
    0.76
    ow
    0.75
    Activations Density 0.000%

    No Known Activations