© 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. 133375
    Prev
    Next
    INDEX
    Explanations

    original research or original works

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

    XML and code punctuation

    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
     uses
    0.28
    <0x0D>
    0.26
       
    0.25
     fitted
    0.25
    n
    0.24
     evaporated
    0.23
     Berlin
    0.23
     Cambridge
    0.23
     using
    0.23
    0.23
    POSITIVE LOGITS
    𝓸
    0.32
    🥰
    0.31
    ਾਰੇ
    0.31
     그리고
    0.31
    𝓪
    0.30
    寶寶
    0.30
     รวมถึง
    0.30
    殮
    0.29
     മറ്റ്
    0.29
     स्वर्ग
    0.29
    Activations Density 0.009%

    No Known Activations