© 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. 168425
    Prev
    Next
    INDEX
    Explanations

    cancer risks and research

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

    cancer treatment, risk, prevention

    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
    ور
    0.73
     감
    0.66
    یم
    0.66
    skiej
    0.65
     ಜಿಲ್ಲ
    0.65
     장애
    0.63
    リス
    0.63
    र्ट
    0.62
     symptom
    0.62
     නිර්
    0.61
    POSITIVE LOGITS
     at
    0.79
    u
    0.61
    otage
    0.60
     Shant
    0.60
    t
    0.58
    et
    0.58
     Riot
    0.57
    碴
    0.56
    <unused635>
    0.56
     for
    0.56
    Activations Density 0.013%

    No Known Activations