© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 87156
    Prev
    Next
    INDEX
    Explanations

    phrases ending in here

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

    placeholder instruction

    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
    Negative Logits
     Ge
    0.51
     Gaussian
    0.48
     here
    0.48
     K
    0.47
     Bont
    0.47
    िएंट
    0.46
    /
    0.46
     State
    0.46
    :
    0.45
     Geelong
    0.45
    POSITIVE LOGITS
    ნიშვნ
    0.51
    exemple
    0.49
    এবং
    0.47
    omitem
    0.47
    ನಾಡ
    0.46
    時候
    0.45
    ayam
    0.45
    debate
    0.45
    bromide
    0.45
    always
    0.45
    Activations Density 0.001%

    No Known Activations