© 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. 6958
    Prev
    Next
    INDEX
    Explanations

    good luck

    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
    з
    1.67
     comedies
    1.43
     Constituency
    1.42
     poems
    1.41
    囗
    1.41
     frugal
    1.39
     Virology
    1.38
     influence
    1.36
     constituencies
    1.36
     Seesaw
    1.36
    POSITIVE LOGITS
    sız
    2.00
    نیا
    1.84
    sul
    1.80
    sf
    1.78
    ncia
    1.77
    sat
    1.73
    و
    1.73
    så
    1.72
    тэй
    1.72
    ówki
    1.71
    Activations Density 0.003%

    No Known Activations