© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9993
    Prev
    Next
    INDEX
    Explanations

    listing items after "include"

    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
    ك
    1.26
    ت
    1.23
    א
    1.20
    و
    1.14
    ي
    1.13
    ה
    1.13
    י
    1.05
    م
    1.02
    ם
    1.01
     volna
    1.00
    POSITIVE LOGITS
     ہیں۔
    0.71
     распростран
    0.69
    teilung
    0.68
     специалисты
    0.68
    場合があります
    0.68
    ่ง
    0.65
    STOCK
    0.64
     সালে
    0.63
    ،
    0.63
    ou
    0.63
    Activations Density 0.031%

    No Known Activations