© 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. 8263
    Prev
    Next
    INDEX
    Explanations

    quantifiers for possibilities

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

    quantifiers such as all, each, every

    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
    长大
    0.46
    同学们
    0.43
    誇
    0.41
    烛
    0.41
     შორის
    0.40
    ubwa
    0.39
    说什么
    0.39
     fenómenos
    0.39
    夸
    0.39
     khắp
    0.38
    POSITIVE LOGITS
     value
    0.44
     pair
    0.44
     ക
    0.43
     ሶ
    0.43
    MQTT
    0.42
     rate
    0.42
     REG
    0.42
     M
    0.42
    TEXT
    0.41
    CDF
    0.41
    Activations Density 0.004%

    No Known Activations