© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 5851
    Prev
    Next
    INDEX
    Explanations

    more specific

    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
    कर
    0.93
    g
    0.82
    IA
    0.77
    2
    0.74
    ार्ज
    0.71
     more
    0.70
    り
    0.70
    v
    0.70
    X
    0.70
    4
    0.68
    POSITIVE LOGITS
     Farley
    0.73
    ທີ່ຈະ
    0.69
    endian
    0.67
     ដើម្បី
    0.67
     pitiful
    0.66
     установки
    0.65
    ilerini
    0.65
    Мне
    0.64
     पिंक
    0.64
    uds
    0.64
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.