© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 61419
    Prev
    Next
    INDEX
    Explanations

    dried fruit and candy

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

    technologies developed for applications

    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
    Timestamp
    0.50
     مكتب
    0.49
    លោក
    0.49
    axios
    0.48
    Metadata
    0.46
    🛖
    0.46
    詳しくは
    0.45
     onderzoek
    0.45
    서
    0.45
    स्वागत
    0.45
    POSITIVE LOGITS
     five
    0.53
     candy
    0.50
     blueberries
    0.50
     assorted
    0.47
    candy
    0.46
     healthier
    0.45
     cleaned
    0.45
     Dried
    0.45
     healthful
    0.44
     Cup
    0.44
    Activations Density 0.002%

    No Known Activations