© 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. 1801
    Prev
    Next
    INDEX
    Explanations

    shopping

    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
     Wound
    0.69
    ма
    0.68
    и
    0.64
    Arena
    0.63
     Arena
    0.61
     I
    0.61
    Merge
    0.61
    い
    0.61
    相
    0.60
    ILL
    0.60
    POSITIVE LOGITS
     urte
    0.71
     kože
    0.68
     jei
    0.68
    cześ
    0.66
    있는
    0.65
     muffins
    0.65
     comerciais
    0.65
     feita
    0.64
     lindos
    0.64
     skirts
    0.64
    Activations Density 0.004%

    No Known Activations