© 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-16K
    7. 1806
    Prev
    Next
    INDEX
    Explanations

    standard operating procedures

    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_16k_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
    。
    0.85
     foothills
    0.83
    $_
    0.81
     કરીને
    0.81
            
    0.80
     ہوئے
    0.79
     nhạc
    0.79
    allele
    0.79
    езде
    0.79
     bluegrass
    0.79
    POSITIVE LOGITS
    ل
    0.92
    ور
    0.92
    Ⲥ
    0.90
     расскажем
    0.84
    ṭ
    0.83
    ur
    0.81
    لن
    0.80
    ল
    0.80
     luat
    0.79
     CCP
    0.77
    Activations Density 0.001%

    No Known Activations