© 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-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 6168
    Prev
    Next
    INDEX
    Explanations

    video game or conferencing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ﺪ
    0.67
    Sed
    0.66
    Modeling
    0.66
    Чи
    0.65
    не
    0.64
    дный
    0.64
    dades
    0.63
    hydro
    0.62
    Executing
    0.61
    له
    0.60
    POSITIVE LOGITS
    oteca
    0.66
     conferencing
    0.64
     Greetings
    0.63
    🎞
    0.63
    iliar
    0.61
    ography
    0.60
    worm
    0.59
    क्ष्य
    0.58
     nibb
    0.57
     crews
    0.57
    Activations Density 0.075%

    No Known Activations