© 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. 133351
    Prev
    Next
    INDEX
    Explanations

    data and sources

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

    we holds his actions

    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
    👟
    0.48
    akaranam
    0.46
     פאר
    0.46
    쿡
    0.45
    興
    0.45
    쫑
    0.45
     एर
    0.45
    ใหญ่
    0.44
    \},
    0.44
     আরব
    0.44
    POSITIVE LOGITS
    ن
    0.62
    主要的
    0.52
    م
    0.47
    ft
    0.46
     clues
    0.44
     muestras
    0.44
     propias
    0.43
     afterthought
    0.43
     cốt
    0.43
     áreas
    0.43
    Activations Density 0.000%

    No Known Activations