© 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. 204771
    Prev
    Next
    INDEX
    Explanations

    data preservation

    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
    ゐ
    0.39
    ም።
    0.38
    はお
    0.38
    ၸ
    0.38
     अराज
    0.37
    详细
    0.36
     तहरीर
    0.36
     बु
    0.35
    गराज
    0.35
    ERT
    0.35
    POSITIVE LOGITS
    Conversation
    0.41
     water
    0.38
     populated
    0.37
     conversation
    0.37
     水
    0.37
     pressurized
    0.36
     Water
    0.36
     vapor
    0.36
    Water
    0.36
     focal
    0.36
    Activations Density 0.001%

    No Known Activations