© 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. 8004
    Prev
    Next
    INDEX
    Explanations

    non-standard or hybrid forms

    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
     القاهرة
    0.56
    对照
    0.55
     malloc
    0.54
     シンプル
    0.51
    측
    0.50
     điển
    0.49
    UpInside
    0.48
    💵
    0.48
     KMeans
    0.48
     negó
    0.48
    POSITIVE LOGITS
     hybrids
    0.95
    Non
    0.85
     non
    0.84
     Non
    0.84
     ट्रांसजेंडर
    0.79
     quasi
    0.76
     Amish
    0.76
     गैर
    0.73
     hybrid
    0.71
     asteroids
    0.71
    Activations Density 1.576%

    No Known Activations