© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 23900
    Prev
    Next
    INDEX
    Explanations

    Databricks platform and its features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kota
    0.42
     Koi
    0.40
    Kota
    0.40
    汐
    0.40
     कं
    0.39
     Saal
    0.39
     Timestamp
    0.38
     skeleton
    0.38
    fänger
    0.38
     eCommerce
    0.38
    POSITIVE LOGITS
     collaborative
    0.43
    Unified
    0.40
    驰
    0.40
    ені
    0.39
    Reli
    0.38
    协作
    0.38
     open
    0.38
     creator
    0.38
    统一
    0.38
     creators
    0.38
    Activations Density 0.002%

    No Known Activations