© 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
    5. 12-GEMMASCOPE-2-RES-16K
    7. 164
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_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
    ﺽ
    0.88
     crumpled
    0.83
     cheered
    0.82
     volonté
    0.82
    mw
    0.79
     μό
    0.79
     гром
    0.78
     Freighter
    0.78
    ва
    0.77
    𝐀
    0.77
    POSITIVE LOGITS
    of
    0.93
    此同时
    0.90
    or
    0.83
    泻
    0.82
    etc
    0.81
    ativas
    0.79
    un
    0.76
    वन
    0.75
     agric
    0.75
    地形
    0.75
    Activations Density 0.000%

    No Known Activations