© 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. 31-GEMMASCOPE-2-RES-262K
    7. 46764
    Prev
    Next
    INDEX
    Explanations

    CPU design, hardware, software

    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_31_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
    䂝
    0.45
    咡
    0.45
    溶
    0.45
    ད་
    0.44
    令和
    0.43
     කළ
    0.42
     የአ
    0.41
    盐
    0.41
    ற்க
    0.41
    选题
    0.41
    POSITIVE LOGITS
     licensees
    0.79
     OEMs
    0.63
     chipset
    0.63
     developers
    0.62
     partners
    0.62
     manufacturers
    0.61
     partnered
    0.61
     consortium
    0.61
     partnerships
    0.60
     implementations
    0.59
    Activations Density 0.103%

    No Known Activations