© 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. 31-GEMMASCOPE-2-RES-16K
    7. 2637
    Prev
    Next
    INDEX
    Explanations

    of

    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
    식이
    0.52
    ાર્થ
    0.51
     القاهرة
    0.49
     অপরিচিত
    0.48
    платно
    0.48
     различными
    0.48
     proximité
    0.48
    舗
    0.48
    ברים
    0.48
     prawd
    0.47
    POSITIVE LOGITS
     của
    3.58
     ofthe
    3.36
     của
    3.33
    ของ
    3.30
     of
    3.20
     של
    2.84
     της
    2.67
    ຂອງ
    2.64
     των
    2.33
     ของ
    2.31
    Activations Density 0.651%

    No Known Activations