© 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
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14701
    Prev
    Next
    INDEX
    Explanations

    numbers and counts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ar
    0.92
    em
    0.81
    mada
    0.78
    ic
    0.78
    es
    0.76
     Log
    0.76
    ى
    0.76
    arag
    0.76
     Teen
    0.75
    egal
    0.73
    POSITIVE LOGITS
     टूर्
    0.81
     lipoproteins
    0.74
     ამ
    0.74
     rupani
    0.72
    िलों
    0.72
     strumenti
    0.72
    ChangeEvent
    0.72
    𝐱
    0.71
     उपाध्यक्ष
    0.70
     गोइंग
    0.70
    Activations Density 0.000%

    No Known Activations