© 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. 12609
    Prev
    Next
    INDEX
    Explanations

    different approach to explaining

    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
    ÓN
    0.91
     Baran
    0.86
     dior
    0.86
    INE
    0.84
     BFS
    0.84
    руют
    0.81
    ATION
    0.80
    莠
    0.80
    ANTE
    0.80
     Jurgen
    0.79
    POSITIVE LOGITS
    bies
    0.85
    ва
    0.79
    selt
    0.77
    。
    0.75
    closePath
    0.75
    س
    0.75
    anlage
    0.74
    a
    0.73
    o
    0.73
    ان
    0.71
    Activations Density 0.000%

    No Known Activations