© 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. 12-GEMMASCOPE-2-RES-16K
    4. 304
    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
    о
    0.94
    ра
    0.89
    rakt
    0.80
    ų
    0.79
    ал
    0.78
    č
    0.78
    𝕚
    0.77
    у
    0.76
    ס
    0.75
    idagi
    0.73
    POSITIVE LOGITS
    THING
    0.90
     Ironically
    0.85
    Worth
    0.83
     nausea
    0.80
    :
    0.80
     Reforms
    0.79
     cauldron
    0.79
     hysteria
    0.77
    yty
    0.77
     spine
    0.76
    Activations Density 0.000%

    No Known Activations