© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 204676
    Prev
    Next
    INDEX
    Explanations

    import Enum

    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/layer_40_width_262k_l0_medium
    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
    हारा
    0.42
     নিতান্ত
    0.42
    Lopez
    0.41
     انگری
    0.41
    ＞
    0.40
     Revealed
    0.38
    /**/*
    0.38
     déjeuner
    0.38
    Wrapped
    0.38
     Wrapped
    0.37
    POSITIVE LOGITS
     composition
    0.39
     slowmotion
    0.38
     isto
    0.37
    펜
    0.36
    naden
    0.36
    ismatch
    0.36
     Ту
    0.35
     punishment
    0.35
    ﺡ
    0.35
     punishments
    0.35
    Activations Density 0.000%

    No Known Activations