© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7444
    Prev
    Next
    INDEX
    Explanations

    George (people and places)

    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
     standard
    0.61
     상관
    0.58
    惚
    0.58
     memory
    0.54
    Along
    0.54
     padrões
    0.53
     cutting
    0.53
    __'
    0.52
     boundaries
    0.52
     گزارش
    0.52
    POSITIVE LOGITS
     Clooney
    0.72
    टेज
    0.58
    CBUUID
    0.55
    ashington
    0.52
     Orwell
    0.51
     PartialEq
    0.50
    Ⓘ
    0.50
    eradish
    0.50
    ক্তিক
    0.50
     clickable
    0.49
    Activations Density 0.042%

    No Known Activations