© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 1564
    Prev
    Next
    INDEX
    Explanations

    use or `use` followed by things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     marihuana
    1.74
    =(-
    1.72
     hypoglycemia
    1.65
     зоны
    1.64
    ه‌ها
    1.64
    =-
    1.62
    =[-
    1.61
    봇
    1.60
    ={"
    1.58
    rpart
    1.58
    POSITIVE LOGITS
    native
    0.77
     native
    0.73
    accurate
    0.71
     prettiest
    0.69
     accurate
    0.65
    original
    0.65
     freshest
    0.61
    natives
    0.61
     Native
    0.61
     latest
    0.58
    Activations Density 0.231%

    No Known Activations