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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 6838
    Prev
    Next
    INDEX
    Explanations

    maximum coverage or value

    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
     причем
    2.03
     portes
    1.86
    𝑝
    1.77
    ति
    1.76
     laine
    1.73
    り
    1.73
     cercanos
    1.68
    ۷
    1.67
     meilleurs
    1.66
    projet
    1.65
    POSITIVE LOGITS
    ים
    2.80
    िमम
    2.19
    s
    2.17
    sız
    2.08
    ется
    2.03
    ق
    1.91
    та
    1.88
    dır
    1.88
    もなく
    1.87
    テナンス
    1.87
    Activations Density 0.175%

    No Known Activations