© 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. 14525
    Prev
    Next
    INDEX
    Explanations

    warranties

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

    bursts, talking, LEGO, city, smart, fats, access

    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
    畂
    0.50
    거나
    0.49
     Missing
    0.49
    Landscape
    0.49
    粼
    0.49
    ющую
    0.48
    ющей
    0.47
    த்தால்
    0.47
     информацией
    0.47
    🐉
    0.46
    POSITIVE LOGITS
     booze
    0.56
    serviceTime
    0.49
     pharmacy
    0.49
     virtues
    0.49
     medicines
    0.48
     creatinine
    0.48
     vigilant
    0.47
     sufficient
    0.46
     mutually
    0.46
     complaining
    0.46
    Activations Density 0.002%

    No Known Activations