© 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. 31-GEMMASCOPE-2-RES-262K
    7. 50500
    Prev
    Next
    INDEX
    Explanations

    pdf related generation or reading

    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
    el
    0.84
    t
    0.78
    :
    0.72
    l
    0.66
    ac
    0.65
    em
    0.62
    ),
    0.61
    a
    0.61
    ler
    0.61
    ڈ
    0.61
    POSITIVE LOGITS
    هاي
    0.59
     مي‌
    0.58
     getImage
    0.58
     dukkham
    0.57
    యే
    0.56
    лло
    0.56
    ర్య
    0.54
     étro
    0.54
    وتي
    0.54
    سيط
    0.54
    Activations Density 0.002%

    No Known Activations