© 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. 59294
    Prev
    Next
    INDEX
    Explanations

    family sailing

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

    programmatic context

    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
    ם
    0.80
    海道
    0.53
    פ
    0.53
    與
    0.52
    נ
    0.49
    ﾌ
    0.49
    भ
    0.48
    দাতা
    0.47
    ﻌ
    0.47
    ਸ
    0.46
    POSITIVE LOGITS
     Hesse
    0.55
     کردی
    0.51
     mał
    0.49
     Jiří
    0.49
     Schwarzen
    0.43
     Justice
    0.43
    dog
    0.43
     Leipzig
    0.43
     savers
    0.43
     nationally
    0.43
    Activations Density 0.000%

    No Known Activations