© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 222438
    Prev
    Next
    INDEX
    Explanations

    endothelial function

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

    predicting future problems

    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
     Cancer
    0.46
    ;
    0.46
     Asthma
    0.46
     abortions
    0.46
     Drugs
    0.45
     intended
    0.44
     extensive
    0.44
    I
    0.44
     originates
    0.43
     obesity
    0.43
    POSITIVE LOGITS
    ຂໍ້ມ
    0.53
    氇
    0.45
    跇
    0.44
     لاحظ
    0.44
     закончи
    0.43
     cx
    0.43
    咟
    0.43
    淥
    0.42
    ফর
    0.42
     начну
    0.42
    Activations Density 0.001%

    No Known Activations