© 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. 5408
    Prev
    Next
    INDEX
    Explanations

    questions and prompts

    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
     defocused
    0.75
    imagem
    0.68
    izr
    0.68
    有的
    0.68
    भूति
    0.68
    ﯼ
    0.66
     Pasteur
    0.66
    Aqui
    0.66
     celulares
    0.65
     lik
    0.63
    POSITIVE LOGITS
     ſt
    0.76
    achricht
    0.73
    aad
    0.67
    ложи
    0.67
     త
    0.65
    nent
    0.64
     gäller
    0.64
     หมาย
    0.64
     nationality
    0.63
     initializes
    0.63
    Activations Density 0.003%

    No Known Activations