© 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. 24-GEMMASCOPE-2-RES-16K
    7. 5810
    Prev
    Next
    INDEX
    Explanations

    entry-level, self-made, thread-safe

    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_24_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
    s
    0.72
    ন্থা
    0.67
    iranje
    0.64
    ments
    0.63
    ه‌ها
    0.61
     wird
    0.61
    ції
    0.60
    ability
    0.60
    isation
    0.60
    that
    0.60
    POSITIVE LOGITS
    ‐
    1.01
    ־
    0.95
    -
    0.80
    
    0.78
    ilient
    0.77
     सदस्यीय
    0.76
    -$\
    0.75
    만한
    0.73
    -​
    0.73
    oriented
    0.70
    Activations Density 0.732%

    No Known Activations