© 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. 452
    Prev
    Next
    INDEX
    Explanations

    own things

    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
    s
    0.98
    L
    0.93
    Ll
    0.90
    I
    0.87
    O
    0.82
    M
    0.82
    Ի
    0.82
    pH
    0.81
    i
    0.81
     Lok
    0.80
    POSITIVE LOGITS
     불구하고
    1.04
     pediu
    0.94
     специальных
    0.94
    서는
    0.91
     quinze
    0.91
    ја
    0.90
     ідэ
    0.90
     інших
    0.90
     некоторое
    0.90
     terminou
    0.89
    Activations Density 0.000%

    No Known Activations