© 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. 3278
    Prev
    Next
    INDEX
    Explanations

    are a

    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
    굳
    0.47
     এগুলো
    0.47
     cultivos
    0.47
     bunları
    0.47
     ":
    0.46
    他にも
    0.46
     favorites
    0.45
     fileName
    0.44
    इसमें
    0.44
     comentarios
    0.44
    POSITIVE LOGITS
     our
    0.66
     your
    0.64
     ہمارے
    0.54
     their
    0.53
     two
    0.53
     a
    0.53
     உங்கள்
    0.52
     another
    0.51
     the
    0.50
     some
    0.50
    Activations Density 0.238%

    No Known Activations