© 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. 59
    Prev
    Next
    INDEX
    Explanations

    and followed by a word

    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
    ה
    0.66
     Nej
    0.66
    상
    0.59
    Z
    0.58
     svoj
    0.57
    제
    0.57
    ע
    0.54
     The
    0.54
    Nombre
    0.54
     seves
    0.54
    POSITIVE LOGITS
    ти
    0.68
     whatnot
    0.60
    ৪২
    0.57
    。(
    0.57
    те
    0.56
     verwend
    0.54
    ↵↵
    0.54
    ৪৩
    0.54
     உள்ளது
    0.53
    </h4>
    0.52
    Activations Density 1.703%

    No Known Activations