© 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. 113413
    Prev
    Next
    INDEX
    Explanations

    new technology or ideas

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

    offers starting substring

    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
     term
    0.57
     bead
    0.53
     sch
    0.49
     o
    0.48
     in
    0.48
     community
    0.47
     switch
    0.46
     sib
    0.46
    etar
    0.46
     loci
    0.45
    POSITIVE LOGITS
    ຂໍ້ມ
    0.58
     verfü
    0.54
     ஜெய
    0.52
    প্রশ্ন
    0.52
    ጀም
    0.52
    膯
    0.51
    పై
    0.49
    PolicyQuery
    0.49
    ຜະລ
    0.49
    লেম
    0.49
    Activations Density 0.001%

    No Known Activations