© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 162734
    Prev
    Next
    INDEX
    Explanations

    wanted to, showing of, during a, entertainment and, discharged them

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

    medical surgery, make omelette, finding zeroes

    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
    Not in Any Lists

    No Comments

    Negative Logits
     অনেকগুলি
    0.51
     কয়েকটি
    0.50
     tačiau
    0.50
     নামটি
    0.49
     ትንሽ
    0.49
     ደ
    0.49
     অনেকের
    0.48
     مشکلات
    0.48
     Однако
    0.48
     STILL
    0.48
    POSITIVE LOGITS
    ев
    0.45
    jee
    0.43
    DeleteMapping
    0.42
     burglar
    0.41
     ophthal
    0.41
     prepar
    0.41
     preparatory
    0.41
     fund
    0.40
     위해
    0.39
    耇
    0.39
    Activations Density 0.001%

    No Known Activations