© 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. 16039
    Prev
    Next
    INDEX
    Explanations

    self. followed by a method/attribute

    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
     avion
    0.54
    了他的
    0.53
    ਰੇ
    0.52
    现场
    0.51
     his
    0.50
     ()
    0.50
    私の
    0.50
    秇
    0.50
     various
    0.49
    ()){
    0.47
    POSITIVE LOGITS
     mình
    0.75
     себе
    0.70
     sobie
    0.70
     oneself
    0.70
     தாம்
    0.68
     themselves
    0.67
     вона
    0.67
     мы
    0.66
     cls
    0.66
     usted
    0.65
    Activations Density 0.037%

    No Known Activations