© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 9000
    Prev
    Next
    INDEX
    Explanations

    within arguments type

    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_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
    ↵
    0.94
     Veterans
    0.90
     (
    0.83
    veg
    0.82
     Refugees
    0.81
     Veteran
    0.80
     [
    0.77
     at
    0.76
     checkpoints
    0.75
     Cyprus
    0.75
    POSITIVE LOGITS
     algebraica
    0.93
    льний
    0.92
     instantiated
    0.90
    ieza
    0.89
     metrizable
    0.89
     deleter
    0.87
     prokary
    0.87
     Voiture
    0.86
     Prothorax
    0.86
     breech
    0.86
    Activations Density 0.994%

    No Known Activations