© 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. 15776
    Prev
    Next
    INDEX
    Explanations

    it is

    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
     *,
    0.78
     ada
    0.66
     qualquer
    0.66
     sez
    0.66
     bolo
    0.64
     =,
    0.64
     '*',
    0.63
     digraph
    0.63
     bunu
    0.61
     `:`,
    0.61
    POSITIVE LOGITS
     Именно
    0.64
     Саме
    0.59
    才会
    0.58
    띤
    0.57
    Kết
    0.57
    才會
    0.56
     তিনিই
    0.54
    흠
    0.54
    nosti
    0.54
    THAT
    0.54
    Activations Density 0.052%

    No Known Activations