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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 601
    Prev
    Next
    INDEX
    Explanations

    geographic locations and programming terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dirigeants
    0.78
     visitar
    0.75
     renovated
    0.75
    ⴼ
    0.74
     incumbent
    0.73
    asitriangular
    0.73
     contará
    0.73
     betrayed
    0.73
     complainant
    0.72
     vaccinate
    0.72
    POSITIVE LOGITS
    en
    0.72
    ,
    0.68
    .
    0.64
     แล้ว
    0.60
    aat
    0.59
     that
    0.58
     مع
    0.57
    .<
    0.57
     Nah
    0.57
     прямо
    0.57
    Activations Density 0.017%

    No Known Activations