© 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. 226440
    Prev
    Next
    INDEX
    Explanations

    requests certain

    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
     ਦਿ
    0.46
     dañ
    0.45
     podob
    0.44
    ਟ
    0.44
     uš
    0.44
     someone
    0.43
     mulch
    0.43
     pedestrians
    0.42
     Prasad
    0.42
    ように
    0.42
    POSITIVE LOGITS
    widetilde
    0.52
    జే
    0.45
    issima
    0.45
    维
    0.45
    官网
    0.44
    带着
    0.44
     Envelope
    0.44
    这
    0.44
    锤
    0.43
    Modal
    0.42
    Activations Density 0.002%

    No Known Activations