© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 31948
    Prev
    Next
    INDEX
    Explanations

    throat and swallowing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_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
    ᠬ
    0.38
     fem
    0.38
     analytic
    0.38
     ताब
    0.38
     енер
    0.38
     pram
    0.38
     Analytic
    0.37
     diber
    0.36
    翠
    0.36
    🇴
    0.36
    POSITIVE LOGITS
     throat
    1.88
     Throat
    1.77
    throat
    1.68
     throats
    1.64
    喉
    1.49
    Thro
    1.42
     swallowing
    1.35
    咽
    1.30
     swallow
    1.28
     swallowed
    1.26
    Activations Density 0.026%

    No Known Activations