© 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. 3641
    Prev
    Next
    INDEX
    Explanations

    vaccination

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

    vaccine and vaccination

    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
     패턴
    0.56
     함수
    0.54
     미술
    0.52
    衾
    0.52
    妣
    0.51
    股东
    0.50
     좌표
    0.50
    绫
    0.49
     도형
    0.49
     요소
    0.49
    POSITIVE LOGITS
     vaccine
    1.55
     vaccines
    1.50
     vaccination
    1.42
     Vaccine
    1.42
     vaccinations
    1.41
     Vaccines
    1.34
     vaccinated
    1.33
     vaccin
    1.31
     Vaccination
    1.30
    vacc
    1.29
    Activations Density 0.040%

    No Known Activations