© 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. 110048
    Prev
    Next
    INDEX
    Explanations

    terminal illness

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

    breakthrough innovations

    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
     Jerman
    0.50
    но
    0.49
    новый
    0.47
     Soci
    0.46
    持つ
    0.45
    주
    0.45
    testGet
    0.44
     Specifically
    0.43
     Janeiro
    0.43
     nồi
    0.43
    POSITIVE LOGITS
     بے
    0.52
     recite
    0.47
     condoms
    0.42
     braces
    0.42
    nahme
    0.41
    {\
    0.41
     সাব
    0.40
     whisper
    0.40
     whispered
    0.39
    Bread
    0.39
    Activations Density 0.000%

    No Known Activations