© 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. 31940
    Prev
    Next
    INDEX
    Explanations

    aggressive actions

    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
    lardan
    1.83
    น์
    1.75
    ,
    1.69
    ことにより
    1.67
    ла
    1.65
    fledged
    1.65
    mogorov
    1.64
    ことで
    1.61
    นะ
    1.59
    rk
    1.57
    POSITIVE LOGITS
    ö
    1.58
    ş
    1.53
     spate
    1.52
     savor
    1.51
    ung
    1.48
    ри
    1.45
    ем
    1.42
    টে
    1.39
    ście
    1.38
    ut
    1.36
    Activations Density 0.003%

    No Known Activations