© 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. 91019
    Prev
    Next
    INDEX
    Explanations

    He was told to

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

    subjects performing actions

    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
     drawSprites
    0.47
     இல்லை
    0.45
     ไม่มี
    0.44
     randomness
    0.44
     něco
    0.43
     bilmi
    0.43
     不是
    0.43
     பாதிக்கிறது
    0.43
     nějak
    0.42
     有
    0.42
    POSITIVE LOGITS
     wówczas
    0.55
     alors
    0.55
     এতটাই
    0.53
    这才
    0.50
    alors
    0.50
     daarbij
    0.49
     specifically
    0.47
     настолько
    0.47
     notamment
    0.46
     अगदी
    0.46
    Activations Density 0.086%

    No Known Activations