© 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. 85179
    Prev
    Next
    INDEX
    Explanations

    actions and transitions

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

    fresh start

    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
    lesssim
    0.45
     mentioned
    0.43
    有點
    0.41
    ‡
    0.40
    unfortunately
    0.40
    但是在
    0.40
     unfortunately
    0.39
     i
    0.39
     leaflets
    0.38
     thereof
    0.38
    POSITIVE LOGITS
    必须
    0.45
     속에
    0.42
     позволяют
    0.40
     모든
    0.40
     permet
    0.40
     संसार
    0.39
     স্বয়ং
    0.39
     настолько
    0.39
     각
    0.39
    веря
    0.39
    Activations Density 0.005%

    No Known Activations