© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 202792
    Prev
    Next
    INDEX
    Explanations

    sql string literals

    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
    stdio
    0.49
    扩
    0.47
    cott
    0.45
    תה
    0.44
    кой
    0.44
     orientation
    0.44
    es
    0.43
    示
    0.43
     furnishing
    0.42
    释
    0.42
    POSITIVE LOGITS
    (
    0.57
    (?:
    0.55
     felicidade
    0.51
     pendapatan
    0.50
     jasa
    0.48
     telepon
    0.48
     jovens
    0.47
     kumb
    0.47
     crianças
    0.46
     filhos
    0.46
    Activations Density 0.003%

    No Known Activations