© 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. 1370
    Prev
    Next
    INDEX
    Explanations

    of absolute

    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
     of
    1.31
    ของการ
    1.17
    of
    1.03
     của
    0.95
    ของ
    0.92
    の
    0.91
    의
    0.91
     של
    0.84
     for
    0.82
    for
    0.82
    POSITIVE LOGITS
     zusätzlichen
    0.87
     zusätzliche
    0.85
     använda
    0.79
     biofilms
    0.77
     madame
    0.77
     macarons
    0.77
     innych
    0.77
     biomarkers
    0.77
     ulteriori
    0.77
     ample
    0.76
    Activations Density 0.275%

    No Known Activations