© 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. 8575
    Prev
    Next
    INDEX
    Explanations

    26

    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
    ف
    1.15
    ش
    1.05
    า
    1.00
    ح
    0.98
    ни
    0.95
    מ
    0.91
    чатку
    0.90
    ق
    0.88
    ير
    0.86
    ం
    0.86
    POSITIVE LOGITS
    embrie
    0.75
     hãng
    0.74
    two
    0.73
    lover
    0.73
    Time
    0.73
    Haw
    0.72
    logger
    0.72
    Constant
    0.71
    woman
    0.71
    ",
    0.70
    Activations Density 0.003%

    No Known Activations