© 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. 15484
    Prev
    Next
    INDEX
    Explanations

    How to explain or calculate

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

    how to followed by a verb

    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
     आर्टिकल
    0.42
     dersimizde
    0.42
     paragra
    0.41
     shorthand
    0.39
    你想
    0.39
     Bremen
    0.39
     👇
    0.39
     이번
    0.38
     createArticle
    0.38
    你去
    0.38
    POSITIVE LOGITS
    achron
    0.50
    が高
    0.44
    Tcp
    0.44
     statistically
    0.44
     Stochastic
    0.44
     discrepancies
    0.43
     सैन्य
    0.43
    Über
    0.42
     genü
    0.41
    Share
    0.41
    Activations Density 0.028%

    No Known Activations