© 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. 5859
    Prev
    Next
    INDEX
    Explanations

    infections from equipment, people, or soldiers

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

    danger, risk, susceptibility, infection

    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
     അതിന്റെ
    0.44
    铭
    0.44
    谋
    0.43
    ประสบการณ์
    0.42
    演绎
    0.41
    定价
    0.41
     стаўкі
    0.41
     эмо
    0.40
     توقع
    0.40
    碐
    0.40
    POSITIVE LOGITS
     infected
    0.96
     contaminated
    0.94
    infected
    0.84
     infect
    0.81
    contaminated
    0.80
     infection
    0.80
     contaminating
    0.77
     unvaccinated
    0.77
     contamination
    0.76
     immunocom
    0.74
    Activations Density 0.165%

    No Known Activations