© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 187205
    Prev
    Next
    INDEX
    Explanations

    ambition, situation, development, issues

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

    many other languages

    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
    Negative Logits
     weapon
    0.47
     subchapter
    0.45
     totalPrice
    0.43
     पेनल
    0.43
     paa
    0.42
     औ
    0.42
     ganar
    0.42
     буде
    0.42
     usb
    0.42
     सड़क
    0.42
    POSITIVE LOGITS
    冷静
    0.50
    ábban
    0.49
    سین
    0.49
    グレー
    0.47
    対処
    0.47
    ITH
    0.46
    セ
    0.46
    ব্লিউ
    0.46
     Programming
    0.45
    
    0.45
    Activations Density 0.000%

    No Known Activations