© 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. 181931
    Prev
    Next
    INDEX
    Explanations

    country, marketing, groups, collection

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

    quaternion units

    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
    
    0.55
    フランス
    0.54
    
    0.52
     negatif
    0.48
    
    0.48
    袍
    0.47
    ⁈
    0.46
    ্টিফি
    0.46
    ग
    0.46
    esquerda
    0.45
    POSITIVE LOGITS
     sections
    0.47
     SQLite
    0.44
     Google
    0.43
     Sections
    0.42
     Youtube
    0.41
     Virtue
    0.41
     ppt
    0.41
     establishments
    0.41
     newsletter
    0.40
     Twitter
    0.40
    Activations Density 0.000%

    No Known Activations