© 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-TRANSCODER-262K
    7. 217085
    Prev
    Next
    INDEX
    Explanations

    nitric oxide and blood pressure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    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
    प्रो
    0.39
     Teg
    0.39
    ライス
    0.39
     Mutter
    0.38
     regardless
    0.37
     प्लस
    0.35
    軺
    0.35
     перево
    0.35
    യെ
    0.34
     Regardless
    0.34
    POSITIVE LOGITS
    GLOBALS
    0.39
    污
    0.39
    
    0.38
    NBA
    0.36
     submar
    0.35
    ointment
    0.35
     hipot
    0.35
     நீரில்
    0.34
     الموسم
    0.34
    海水
    0.34
    Activations Density 0.001%

    No Known Activations