© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7703
    Prev
    Next
    INDEX
    Explanations

    fifty, 50, percentages, currency

    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
     ۲
    1.07
     ૨
    0.95
    
    0.94
     seventeen
    0.92
     ۱۴
    0.92
     ২৭
    0.91
     २
    0.91
     ૧
    0.89
     fourteenth
    0.89
     fourteen
    0.88
    POSITIVE LOGITS
    5
    2.02
     fifty
    1.63
     Fifty
    1.63
    ５
    1.61
     ५
    1.57
     fifties
    1.53
    Fifty
    1.52
    ⁵
    1.52
    ۵
    1.50
    fifty
    1.49
    Activations Density 0.524%

    No Known Activations