© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 61084
    Prev
    Next
    INDEX
    Explanations

    acute lymphoblastic leukemia

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

    terms related to education, academics, and formal qualifications.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on multiword capitalized phrases or titles—sequences of proper-noun style tokens (e.g. “Student Loan Payments,” “Fifty Shades,” “Acute Lymphoblastic Leukemia”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵↵
    -1.66
     one
    -1.48
     такой
    -1.43
    ◥
    -1.42
    หนึ่ง
    -1.40
     одним
    -1.38
    дной
    -1.38
    一個
    -1.36
     vanwege
    -1.35
     différences
    -1.31
    POSITIVE LOGITS
     a
    1.41
    の使用
    1.31
     the
    1.31
    닫
    1.27
     investigates
    1.25
    mbito
    1.25
    glColor
    1.23
    udière
    1.23
    PreInfinity
    1.19
    が付いて
    1.19
    Activations Density 0.087%

    No Known Activations