© 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. 210155
    Prev
    Next
    INDEX
    Explanations

    locations and entities

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

    breakdown of why and what

    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
     striis
    0.58
     masterpieces
    0.49
    しやすい
    0.47
    มัน
    0.46
    ם
    0.45
    全体
    0.45
    各式
    0.45
    ーツ
    0.44
     다양
    0.44
    ፫
    0.44
    POSITIVE LOGITS
     Coinbase
    0.62
     Shopify
    0.57
     Merseyside
    0.56
     Nasdaq
    0.54
     Cumbria
    0.54
     Nigeria
    0.54
     BuzzFeed
    0.54
     Vodafone
    0.53
     ২০১৯
    0.52
     Brexit
    0.51
    Activations Density 0.000%

    No Known Activations