© 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. 38703
    Prev
    Next
    INDEX
    Explanations

    list item continuation

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

    Bing, Mars, Ag, ESA, routers, BIGINT, snow

    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
     outright
    0.39
    中心
    0.36
    센터
    0.36
    坪
    0.36
     জনে
    0.35
     Toulouse
    0.35
    윰
    0.34
    端
    0.34
    サム
    0.34
    Ej
    0.34
    POSITIVE LOGITS
     portas
    0.41
     acompañado
    0.38
     Jax
    0.38
     accompan
    0.37
     beserta
    0.36
     capuche
    0.36
     companion
    0.36
     irmã
    0.35
     nonostante
    0.34
    origine
    0.34
    Activations Density 0.252%

    No Known Activations