© 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. 88785
    Prev
    Next
    INDEX
    Explanations

    .com / .edu urls

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

    domain.com/ paths

    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
    榇
    0.57
     extensa
    0.47
    为人
    0.46
     tagReport
    0.46
     noastră
    0.45
    كنولوجيا
    0.45
     cidad
    0.45
     داخ
    0.45
     ليست
    0.45
    🏐
    0.45
    POSITIVE LOGITS
     t
    0.52
     z
    0.48
     two
    0.48
     typical
    0.47
     mid
    0.47
     OCT
    0.47
     DQ
    0.47
     the
    0.46
     disintegration
    0.46
     of
    0.45
    Activations Density 0.007%

    No Known Activations