© 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. 6913
    Prev
    Next
    INDEX
    Explanations

    illuminated by light

    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
    brown
    0.63
    Brown
    0.63
    ąz
    0.58
    يب
    0.56
     ブラウン
    0.56
    Crane
    0.56
    埧
    0.54
     merasakan
    0.54
    歹
    0.54
    trombone
    0.54
    POSITIVE LOGITS
     brightness
    2.16
     brightest
    2.09
     bright
    2.06
     brighter
    2.00
     shine
    1.98
     shines
    1.93
     lights
    1.92
     shining
    1.87
    亮度
    1.87
     luminosity
    1.85
    Activations Density 0.413%

    No Known Activations