© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14866
    Prev
    Next
    INDEX
    Explanations

    file or directory paths

    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
     chiama
    0.70
    resTmp
    0.60
     sicuramente
    0.59
     bilayers
    0.58
     पुस्त
    0.57
    ӟ
    0.57
     bū
    0.56
     ontem
    0.56
    ىڭ
    0.56
     básico
    0.55
    POSITIVE LOGITS
     New
    0.59
     M
    0.54
    B
    0.53
    M
    0.52
     Hash
    0.51
    New
    0.51
     Cases
    0.50
    Y
    0.50
     Nursery
    0.50
    ization
    0.50
    Activations Density 0.047%

    No Known Activations