© 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. 40-GEMMASCOPE-2-RES-262K
    7. 13841
    Prev
    Next
    INDEX
    Explanations

    API Gateway Lambda cursor

    np_acts-logits-general · gemini-2.5-flash-lite

    the neuron detects long, formal, structured instructional or official text (documents with headings, sections, and procedural language).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
    我想
    0.46
     kiş
    0.45
    我不
    0.43
    留
    0.42
     siècles
    0.42
    ᵚ
    0.42
    ំនួន
    0.42
     रणबीर
    0.41
    但我
    0.41
     पीओ
    0.40
    POSITIVE LOGITS
     affair
    0.47
     sacks
    0.45
     arrangements
    0.44
     affairs
    0.44
    nav
    0.42
     appears
    0.41
     reaches
    0.41
     Affair
    0.41
    </h3>
    0.40
     disorders
    0.40
    Activations Density 0.049%

    No Known Activations