© 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. 512
    Prev
    Next
    INDEX
    Explanations

    foreign script or character

    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
    ../../../
    0.69
    它
    0.66
    ς
    0.64
    prehensive
    0.64
    minent
    0.64
     This
    0.63
    ../../
    0.63
    This
    0.62
     povez
    0.61
    mitting
    0.59
    POSITIVE LOGITS
    其它
    0.80
    ্ড
    0.76
    টি
    0.75
    िया
    0.71
    на
    0.65
     ίδια
    0.65
    к
    0.63
    ти
    0.62
     други
    0.62
    இல்
    0.62
    Activations Density 2.881%

    No Known Activations