© 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. 12-GEMMASCOPE-2-RES-16K
    7. 14404
    Prev
    Next
    INDEX
    Explanations

    what ... looks like

    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_12_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
     woe
    0.95
    ש
    0.89
     ئەو
    0.85
     truths
    0.83
     Illumina
    0.82
     Vegeta
    0.81
     maíz
    0.81
     foolproof
    0.80
     Genome
    0.79
     extol
    0.78
    POSITIVE LOGITS
    الم
    0.93
     වශයෙන්
    0.87
    ين
    0.82
    خرى
    0.81
     આગળ
    0.81
    А
    0.81
    مش
    0.79
    الش
    0.79
    épend
    0.77
    tų
    0.77
    Activations Density 0.001%

    No Known Activations