© 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. 7651
    Prev
    Next
    INDEX
    Explanations

    a lot of

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

    lots of quantity

    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
    もしくは
    0.28
    ⌦
    0.28
    neath
    0.27
     quelconque
    0.26
     कुनै
    0.26
     linestyle
    0.24
     تاہم
    0.24
     rctx
    0.24
     کدام
    0.24
     ။
    0.24
    POSITIVE LOGITS
     viele
    0.30
    感慨
    0.28
     people
    0.28
     વિવિધ
    0.27
     surprises
    0.27
     народу
    0.27
     людей
    0.26
    많
    0.26
    有很多
    0.26
     liebe
    0.26
    Activations Density 0.616%

    No Known Activations