© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 14755
    Prev
    Next
    INDEX
    Explanations

    program, course, award, advancement, cost

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

    abstract concepts and concrete nouns

    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
    或其他
    0.57
     그러니까
    0.53
     причем
    0.50
    或者
    0.47
     或者
    0.47
    ,*
    0.43
    ،
    0.43
    之类的
    0.43
     или
    0.43
    சாமி
    0.42
    POSITIVE LOGITS
     donning
    0.49
     showcasing
    0.48
     identifying
    0.46
    ကာ
    0.46
     capturing
    0.46
     athleticism
    0.46
     لت
    0.44
     forhold
    0.43
    1
    0.43
     identification
    0.43
    Activations Density 0.249%

    No Known Activations