© 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. 60477
    Prev
    Next
    INDEX
    Explanations

    scale

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

    burns and interference

    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
    廠
    0.48
    Н
    0.47
    दे
    0.47
    ယောက်
    0.46
     Groot
    0.46
    Drops
    0.46
     प्रोफाइल
    0.46
    drops
    0.46
     बनी
    0.45
    
    0.45
    POSITIVE LOGITS
    ويم
    0.52
    aliya
    0.50
     northwestern
    0.49
     s
    0.43
     ܕ
    0.43
     reconstruct
    0.42
     lemon
    0.41
     tear
    0.41
     torneo
    0.41
    ן
    0.41
    Activations Density 0.000%

    No Known Activations