© 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. 132942
    Prev
    Next
    INDEX
    Explanations

    mostly locations

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

    gardening watering terms

    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
    裝置
    0.49
    僮
    0.47
     প্রস্থ
    0.43
     entsteht
    0.43
     いつ
    0.43
     Antrieb
    0.42
    Ỳ
    0.42
     ஏற்ப
    0.41
    abilität
    0.41
    乍
    0.41
    POSITIVE LOGITS
     pesquisa
    0.50
    ก
    0.49
     misinformation
    0.46
     Kud
    0.46
    औ
    0.46
    ሻ
    0.46
     sacr
    0.44
    ک
    0.43
     desec
    0.43
     abuse
    0.42
    Activations Density 0.001%

    No Known Activations