© 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. 5369
    Prev
    Next
    INDEX
    Explanations

    streamline workflows, operations, processes, communication

    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
    ැ
    1.61
    <0x80>
    1.55
     اغلب
    1.55
    म
    1.50
    v
    1.48
     принима
    1.45
     ومع
    1.45
     వీటి
    1.45
     एग्
    1.43
     proteg
    1.43
    POSITIVE LOGITS
    יים
    1.95
    лизация
    1.69
    лама
    1.69
    ০
    1.68
     waterways
    1.66
     efficiencies
    1.65
    ल
    1.64
    le
    1.60
    ลด
    1.60
    able
    1.59
    Activations Density 0.006%

    No Known Activations