© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 17987
    Prev
    Next
    INDEX
    Explanations

    mentions of editions

    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_16_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
     đợi
    0.98
    dı
    0.97
    o
    0.96
     pince
    0.90
    ూ
    0.87
     virtu
    0.85
     decis
    0.84
     ١
    0.82
    ्स
    0.81
     richt
    0.81
    POSITIVE LOGITS
    ר
    1.30
    ли
    1.27
    l
    1.27
    প
    1.17
    し
    1.15
    ير
    1.07
    Об
    1.06
    νας
    1.06
    ش
    1.05
    م
    1.04
    Activations Density 0.003%

    No Known Activations