© 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. 76081
    Prev
    Next
    INDEX
    Explanations

    Loading, loaded, cook, read

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

    previews them

    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
    Not in Any Lists

    No Comments

    Negative Logits
    årt
    0.49
    世
    0.48
    אה
    0.47
    加熱
    0.44
    ذه
    0.44
    ياً
    0.44
     industrious
    0.43
    СО
    0.43
    ohid
    0.42
    КИ
    0.42
    POSITIVE LOGITS
     Loaded
    0.59
     APP
    0.51
     Else
    0.48
     формула
    0.46
    ‌కు
    0.46
     ð
    0.46
     તમારી
    0.46
     apprendre
    0.45
     перший
    0.45
     دوسرا
    0.44
    Activations Density 0.001%

    No Known Activations