© 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. 31-GEMMASCOPE-2-RES-262K
    7. 18950
    Prev
    Next
    INDEX
    Explanations

    checking existence or conditions

    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
    스크
    0.45
     ალ
    0.45
    สัง
    0.45
     сто
    0.44
    ด
    0.44
     로
    0.43
    ロ
    0.43
    ан
    0.42
    仕方
    0.42
    uoj
    0.42
    POSITIVE LOGITS
     !=
    0.82
    hasClass
    0.79
     είναι
    0.73
     není
    0.73
    isnan
    0.72
     exista
    0.72
    isEmpty
    0.71
     nėra
    0.70
     ikke
    0.70
    hasOwnProperty
    0.70
    Activations Density 0.095%

    No Known Activations