© 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. 7853
    Prev
    Next
    INDEX
    Explanations

    vicuna

    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
    od
    1.93
    ore
    1.91
    ten
    1.86
    1.84
    ts
    1.70
     harmonies
    1.66
    ן
    1.66
    k
    1.66
    liness
    1.59
    in
    1.58
    POSITIVE LOGITS
    には
    1.88
    없는
    1.73
     glauben
    1.73
    不会
    1.70
    ação
    1.63
    了一个
    1.62
     viven
    1.61
    해서
    1.59
    沒有
    1.55
    overflow
    1.55
    Activations Density 0.077%

    No Known Activations