© 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. 52259
    Prev
    Next
    INDEX
    Explanations

    new developments, IRS, GPUs, typed arrays

    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
    刮
    0.53
    ί
    0.50
    ø
    0.45
    μ
    0.44
    风
    0.43
    it
    0.43
    勤務
    0.43
    which
    0.42
    仕事
    0.42
     controvers
    0.42
    POSITIVE LOGITS
    कक्ष
    0.50
     abound
    0.48
     дума
    0.46
     задума
    0.45
    𐰴
    0.45
     говори
    0.45
    हालय
    0.44
    CAUSE
    0.43
    lusconi
    0.43
     abut
    0.43
    Activations Density 0.001%

    No Known Activations