© 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. 170
    Prev
    Next
    INDEX
    Explanations

    formatting characters

    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_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
     the
    0.76
     a
    0.61
     an
    0.56
     increased
    0.54
    the
    0.53
     informacje
    0.52
     this
    0.52
     materials
    0.52
     certaines
    0.51
     various
    0.50
    POSITIVE LOGITS
    ↵↵
    0.61
    !">
    0.52
     (>
    0.50
    ,</
    0.50
    ,))
    0.49
    !\
    0.49
    $('
    0.49
    hafte
    0.49
    !“
    0.48
    ,(
    0.48
    Activations Density 2.031%

    No Known Activations