© 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. 145913
    Prev
    Next
    INDEX
    Explanations

    providing fun

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

    instructions, examples, care

    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
    {[
    0.57
    toluene
    0.51
    {(
    0.48
     bumping
    0.48
     southbound
    0.48
     eastbound
    0.46
    ต้า
    0.46
    
    0.46
     westbound
    0.45
    ارا
    0.45
    POSITIVE LOGITS
     τῶν
    0.48
     ವಿವಿಧ
    0.45
    ời
    0.45
    Masters
    0.45
    ın
    0.44
     vier
    0.44
    Materials
    0.44
     brass
    0.43
     விள
    0.43
    Pro
    0.43
    Activations Density 0.000%

    No Known Activations