© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 41-GEMMASCOPE-2-RES-262K
    4. 62261
    Prev
    Next
    INDEX
    Explanations

    list of things

    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
     Live
    0.43
     live
    0.43
    帽子
    0.42
    活
    0.41
     paintball
    0.40
     लाइव
    0.39
     Xbox
    0.39
     LIVE
    0.38
    ライブ
    0.38
     తనకు
    0.38
    POSITIVE LOGITS
    咛
    0.41
    мол
    0.40
    ucaly
    0.39
    管理局
    0.38
    jednoc
    0.35
    |}
    0.35
     Moose
    0.35
     charset
    0.35
    ASTER
    0.35
    +_
    0.35
    Activations Density 0.000%

    No Known Activations