© 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. 103619
    Prev
    Next
    INDEX
    Explanations

    pattern, pathway, rail, sampling, young

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

    learning and user profiles

    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
    Haha
    0.54
    Sai
    0.50
    Sed
    0.49
    Arqu
    0.47
    Fake
    0.46
    Hawk
    0.46
    Namara
    0.45
    ﺼ
    0.44
    Swami
    0.44
    フォルダ
    0.44
    POSITIVE LOGITS
     ofer
    0.53
    abez
    0.52
    riek
    0.52
    iolet
    0.52
    lán
    0.52
     Belgien
    0.52
     où
    0.51
    وفة
    0.50
     bleue
    0.50
    ibirsk
    0.50
    Activations Density 0.002%

    No Known Activations