© 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. 24350
    Prev
    Next
    INDEX
    Explanations

    run command

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

    running scripts with node or python

    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
     scope
    0.46
    制品
    0.44
    Baseline
    0.43
     बेश
    0.43
     झलक
    0.43
    TER
    0.42
     الجديدة
    0.42
    备
    0.42
    靶
    0.41
    Detal
    0.41
    POSITIVE LOGITS
     অথবা
    0.46
     Spirits
    0.45
     yoki
    0.45
     maupun
    0.44
    同一
    0.44
     Sử
    0.42
    ئو
    0.41
     două
    0.41
     కలిసి
    0.41
     ataupun
    0.40
    Activations Density 0.000%

    No Known Activations