© 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. 318
    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
    ס
    0.61
    ן
    0.61
    '.
    0.55
    $%
    0.53
    ри
    0.51
    .
    0.51
    ്രീ
    0.50
    ુ
    0.48
    $.
    0.47
    נו
    0.47
    POSITIVE LOGITS
    daki
    0.54
    0.50
    kte
    0.49
    kant
    0.47
    Rite
    0.46
    ButtonItem
    0.45
    Cantidad
    0.45
    UIntValue
    0.45
     對
    0.45
    CharCode
    0.44
    Activations Density 13.287%

    No Known Activations