© 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. 43179
    Prev
    Next
    INDEX
    Explanations

    pending states

    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
     ascertain
    2.02
    ס
    1.99
     quidem
    1.87
     pasukan
    1.80
    ۳
    1.77
    Έ
    1.77
    Xét
    1.68
    밝
    1.67
    pronged
    1.66
     xong
    1.63
    POSITIVE LOGITS
    其他
    1.80
    ences
    1.76
    ق
    1.72
    ки
    1.69
    elope
    1.67
    ğini
    1.66
    ت
    1.66
    in
    1.60
    ature
    1.60
    ção
    1.55
    Activations Density 0.007%

    No Known Activations