© 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. 72750
    Prev
    Next
    INDEX
    Explanations

    more people

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

    Cattle of the Deep

    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
    ด
    0.51
     blackout
    0.50
     Risiko
    0.49
     disparo
    0.49
     समाजा
    0.48
     Mika
    0.47
     berasal
    0.47
     বুঝিতে
    0.46
     मोठा
    0.46
     cutout
    0.46
    POSITIVE LOGITS
    Ｉ
    0.45
     maximizes
    0.45
    u
    0.45
     самых
    0.44
    Ｒ
    0.43
    我
    0.42
     yan
    0.41
     janu
    0.41
    胿
    0.41
    奧
    0.41
    Activations Density 0.000%

    No Known Activations