© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 3236
    Prev
    Next
    INDEX
    Explanations

    I cannot / will not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_65k_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
    то
    0.54
    ，
    0.54
    y
    0.52
    ,
    0.52
     (
    0.51
    á
    0.48
     quella
    0.43
    quela
    0.43
    고
    0.42
     &
    0.41
    POSITIVE LOGITS
    嶌
    0.50
    ₂+
    0.48
     pengetahuan
    0.48
    ोंग
    0.47
     Gandh
    0.45
     sorghum
    0.44
    ಗಳಿಗೆ
    0.43
     Himalayas
    0.43
     whakap
    0.43
    បន្ថែម
    0.43
    Activations Density 1.966%

    No Known Activations