© 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. 26493
    Prev
    Next
    INDEX
    Explanations

    vaccine production and distribution

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

    vaccine development and deployment

    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
     createFile
    0.59
     स्टाइलिश
    0.53
     remnant
    0.50
    锑
    0.46
     Staub
    0.46
    沉积
    0.45
    careous
    0.45
    ectoria
    0.45
     술
    0.45
    饮食
    0.44
    POSITIVE LOGITS
    vacc
    0.78
     vaccines
    0.76
     vaccine
    0.74
     Vaccine
    0.72
     Vaccines
    0.69
     AstraZeneca
    0.67
    疫苗
    0.66
     vaksin
    0.65
    Vacc
    0.63
     вакци
    0.60
    Activations Density 0.002%

    No Known Activations