© 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. 208206
    Prev
    Next
    INDEX
    Explanations

    websites, wood kitchen items, super Tech, server, Arena, murals

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

    hedge practice

    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
     jullie
    0.47
     ارسال
    0.46
     گردد
    0.46
     ∆
    0.45
     livre
    0.45
     heel
    0.44
     wavelet
    0.44
     შესაძ
    0.44
     setText
    0.44
    іб
    0.43
    POSITIVE LOGITS
     Ohio
    0.50
    埙
    0.45
    โลก
    0.45
     about
    0.44
    ตั้งแต่
    0.43
     Barbados
    0.42
     בית
    0.42
     Karak
    0.42
    others
    0.42
     বাড়ি
    0.42
    Activations Density 0.000%

    No Known Activations