© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 182
    Prev
    Next
    INDEX
    Explanations

    question is/of

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

    depends, varies, condition

    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_16k_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
    ۔
    0.27
    。
    0.25
    ।
    0.24
    ។
    0.24
    \
    0.23
    ',
    0.23
    .\
    0.22
    '.
    0.21
    。\
    0.21
    ，
    0.21
    POSITIVE LOGITS
     seems
    0.23
     είναι
    0.22
     fluctuates
    0.21
     depender
    0.21
     rimane
    0.20
     varies
    0.20
     está
    0.20
     continues
    0.19
     estamos
    0.19
     differs
    0.19
    Activations Density 0.985%

    No Known Activations