© 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-16K
    7. 12917
    Prev
    Next
    INDEX
    Explanations

    whom I

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

    external validation, life lived

    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_16k_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
     reissue
    0.48
     rerun
    0.48
     or
    0.47
     Jump
    0.46
     Terrorism
    0.46
    ,
    0.46
     rer
    0.45
     CAL
    0.44
     U
    0.43
    まれ
    0.43
    POSITIVE LOGITS
     ľudí
    0.54
     kontroll
    0.53
    owego
    0.53
     сотрудников
    0.53
     jobSearch
    0.53
    ierten
    0.52
     estis
    0.52
    ສົ່ງ
    0.52
     étaient
    0.52
     acessórios
    0.50
    Activations Density 0.011%

    No Known Activations