© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 218033
    Prev
    Next
    INDEX
    Explanations

    website, can find, buy, discover

    np_acts-logits-general · gemini-2.5-flash-lite

    functionality and use cases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ிகி
    0.51
    ம
    0.50
    мих
    0.48
    хими
    0.48
    теля
    0.48
    COX
    0.48
    𝐂
    0.48
    इंड
    0.47
    一緒に
    0.47
    ರಿನ
    0.47
    POSITIVE LOGITS
    ill
    0.46
     regol
    0.45
    0.45
     something
    0.45
     well
    0.44
    0
    0.43
     ja
    0.43
     apply
    0.43
     sometimes
    0.43
     hou
    0.43
    Activations Density 0.001%

    No Known Activations