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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 17090
    Prev
    Next
    INDEX
    Explanations

    sore throat

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

    sore or clearing throat

    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_53_width_65k_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
    跏
    0.44
     bici
    0.44
     Occupational
    0.42
    鳜
    0.41
    ්‍ය
    0.40
     oligodendrocyte
    0.39
     Trustee
    0.39
     shipwreck
    0.38
    腿
    0.38
    绻
    0.38
    POSITIVE LOGITS
     throat
    3.27
     Throat
    3.14
     throats
    3.06
    throat
    2.97
    Thro
    2.67
    喉
    2.67
     Thro
    2.00
    咽
    1.98
     THRO
    1.88
    thro
    1.83
    Activations Density 0.031%

    No Known Activations