© 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. 176521
    Prev
    Next
    INDEX
    Explanations

    Location and coverage

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

    dear colleague, camel, how

    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
    扩
    0.57
    SRPI
    0.51
     analyse
    0.50
    RE
    0.49
     échanc
    0.49
     divina
    0.49
     mandib
    0.49
     bri
    0.47
    OMO
    0.47
    спекти
    0.46
    POSITIVE LOGITS
    getAsDouble
    0.45
    futbol
    0.43
    த்தக
    0.42
    ালন
    0.40
    णूक
    0.39
    გ
    0.39
     Tractor
    0.39
     সত্ব
    0.39
     ফেব্রুয়ারি
    0.39
    נן
    0.39
    Activations Density 0.001%

    No Known Activations