Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 4018
    Prev
    Next
    INDEX
    Explanations

    ultrasound imaging

    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
    OutputDir
    1.50
    ea
    1.45
    iend
    1.40
    硗
    1.35
    iin
    1.33
    eş
    1.32
     whatnot
    1.31
    众人
    1.30
    arası
    1.30
    ত্ব
    1.30
    POSITIVE LOGITS
    ח
    1.84
    س
    1.73
    ش
    1.48
    дів
    1.42
    сти
    1.38
    ק
    1.38
    ik
    1.35
    ong
    1.28
     Targets
    1.24
     поиск
    1.24
    Activations Density 0.001%

    No Known Activations