© 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. 24-GEMMASCOPE-2-RES-16K
    7. 1827
    Prev
    Next
    INDEX
    Explanations

    set up or direct others

    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_24_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
    m
    0.80
    injection
    0.80
    o
    0.77
    in
    0.75
    ta
    0.70
    ال
    0.69
    మ
    0.69
    한편
    0.68
    id
    0.68
    aden
    0.68
    POSITIVE LOGITS
     cientos
    1.05
     tengas
    0.90
     hablamos
    0.90
     būti
    0.87
     грошы
    0.87
     tienes
    0.86
     cuidadosamente
    0.86
     aclar
    0.85
     dará
    0.85
    癀
    0.84
    Activations Density 0.003%

    No Known Activations