© 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. 2208
    Prev
    Next
    INDEX
    Explanations

    adventure

    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
    s
    1.64
    ات
    1.63
     fussy
    1.54
     refinery
    1.52
     timezone
    1.50
     disciplinary
    1.43
     defense
    1.41
     차지
    1.40
    تمر
    1.40
    ྦ
    1.39
    POSITIVE LOGITS
    ä
    2.39
    ı
    1.96
    ่
    1.89
    arı
    1.88
    all
    1.84
    au
    1.80
     Aan
    1.79
    েম
    1.78
     Aynı
    1.78
    ิ
    1.78
    Activations Density 0.013%

    No Known Activations