© 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. 9913
    Prev
    Next
    INDEX
    Explanations

    URLs and file paths

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

    links and non-english words

    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
    =
    0.42
    /%
    0.39
    Plugin
    0.35
    Posts
    0.35
    ([],
    0.35
    Linkedin
    0.34
     plugin
    0.33
    ’
    0.33
    /');
    0.33
     Linkedin
    0.33
    POSITIVE LOGITS
     言っ
    0.50
     入っ
    0.44
     स्टार्टिंग
    0.42
     行っ
    0.39
    ultural
    0.38
    মূলক
    0.38
     不过
    0.38
     Flowering
    0.38
     ഉണ്ട്
    0.38
     escolares
    0.38
    Activations Density 0.004%

    No Known Activations