© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1993
    Prev
    Next
    INDEX
    Explanations

    global declaration

    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
    𝙠
    1.13
    Ін
    0.96
    до
    0.95
    蒨
    0.95
    dul
    0.91
    дома
    0.88
    Для
    0.87
     זה
    0.86
    clerosis
    0.86
    don
    0.86
    POSITIVE LOGITS
     unharmed
    0.90
     wichtigen
    0.89
    })(\
    0.86
     th
    0.83
     briefly
    0.82
    roxine
    0.82
     oncoming
    0.81
    稱
    0.80
    ت
    0.80
     optimized
    0.80
    Activations Density 0.011%

    No Known Activations