© 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. 13557
    Prev
    Next
    INDEX
    Explanations

    brand names

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

    OpenAI, guidelines, NFT, website

    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
     schoolchildren
    0.59
    \'{
    0.50
    प्रधानमंत्री
    0.49
     साहित्यिक
    0.48
    mounting
    0.48
    established
    0.46
    {\'
    0.46
     occasioned
    0.46
     τῶν
    0.46
     нередко
    0.46
    POSITIVE LOGITS
     לא
    0.67
     אבל
    0.67
     ل
    0.66
     গুলো
    0.66
     cuz
    0.65
     لا
    0.64
     eles
    0.64
     اي
    0.63
     mags
    0.63
     lvl
    0.62
    Activations Density 0.035%

    No Known Activations