© 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. 31-GEMMASCOPE-2-RES-16K
    7. 16178
    Prev
    Next
    INDEX
    Explanations

    stock grind ft Nebraska to case

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

    disrupts fungal respiration

    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_16k_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
    定律
    0.47
    balancing
    0.46
    ො
    0.46
    관
    0.46
    வா
    0.45
    天氣
    0.44
    зация
    0.44
     nered
    0.43
    र
    0.43
    ୀ
    0.43
    POSITIVE LOGITS
     فت
    0.44
     tủ
    0.43
    ،
    0.43
     Somerville
    0.43
     Biennale
    0.42
     ули
    0.42
     স্বীকৃতি
    0.42
    [(\
    0.42
    اذ
    0.42
     glutathione
    0.42
    Activations Density 0.002%

    No Known Activations