© 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. 220352
    Prev
    Next
    INDEX
    Explanations

    now, but, end sequences

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

    calculator

    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
    ie
    0.53
    0.50
    넴
    0.50
     NON
    0.47
     Non
    0.46
    非
    0.45
    著
    0.45
    록
    0.44
     Curran
    0.44
     Dickinson
    0.43
    POSITIVE LOGITS
     ٹوٹ
    0.51
     evaporate
    0.49
     مرة
    0.49
     معرض
    0.49
    ங்களைக்
    0.48
     apoy
    0.48
     end
    0.48
     آخر
    0.47
     מס
    0.47
     teeming
    0.46
    Activations Density 0.000%

    No Known Activations