© 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. 129217
    Prev
    Next
    INDEX
    Explanations

    you should not

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

    forth programming language

    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
     раст
    0.57
     चेंजेस
    0.54
     ลํา
    0.48
    মায়
    0.48
     इनटू
    0.47
     ज़्यादा
    0.46
     גדול
    0.46
    🐎
    0.46
     ዕ
    0.46
    
    0.46
    POSITIVE LOGITS
    imiz
    0.46
    ventures
    0.46
    Lik
    0.46
     para
    0.43
     test
    0.43
     po
    0.43
    rato
    0.43
    to
    0.42
      
    0.42
    ButtonGroup
    0.42
    Activations Density 0.002%

    No Known Activations