© 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. 107127
    Prev
    Next
    INDEX
    Explanations

    farming and sales information

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

    security and safety

    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
    ู
    0.54
    ง
    0.50
     curved
    0.48
     clearly
    0.48
     mock
    0.47
    풍
    0.47
     faux
    0.47
    '
    0.46
     laund
    0.45
     can
    0.44
    POSITIVE LOGITS
    怎麼樣
    0.54
    lo
    0.52
     natoque
    0.52
     నొప్పి
    0.51
     Antennes
    0.51
     Коло
    0.50
     නිෂ්පා
    0.49
     empezamos
    0.48
     principales
    0.48
    ヂストン
    0.48
    Activations Density 0.000%

    No Known Activations