© 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. 31-GEMMASCOPE-2-RES-16K
    7. 2940
    Prev
    Next
    INDEX
    Explanations

    JSON structure and commands

    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_31_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
    ↵↵
    1.09
        
    0.63
       
    0.60
    ↵
    0.59
    [/
    0.54
    <\/
    0.54
     HOWEVER
    0.52
    -">
    0.50
     एम
    0.48
    🌴
    0.48
    POSITIVE LOGITS
    ምና
    0.58
    finally
    0.57
    Finally
    0.57
    ómago
    0.56
     तैयारियों
    0.52
    лийн
    0.50
    》《
    0.50
    ྱི་
    0.50
    ೇಳ
    0.50
     فأ
    0.50
    Activations Density 0.226%

    No Known Activations