© 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. 208641
    Prev
    Next
    INDEX
    Explanations

    lists, numbers, and labels

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

    block, blocks, security, search

    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
    il
    0.58
    Vi
    0.54
    –
    0.54
    ed
    0.53
    Nj
    0.53
    R
    0.52
    K
    0.52
    Ku
    0.52
    い
    0.52
    ü
    0.52
    POSITIVE LOGITS
     siège
    0.50
     فين
    0.48
    لاث
    0.47
     sasane
    0.47
     carinatis
    0.47
     দীপ
    0.47
     دونك
    0.46
     லட்ச
    0.44
     sétimo
    0.43
     эта
    0.43
    Activations Density 0.000%

    No Known Activations