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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10543
    Prev
    Next
    INDEX
    Explanations

    Lenin created, SimpleDateFormat sdf, LT Lover

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

    The neuron identifies capitalized multi-letter tokens—proper names, acronyms, and class or type identifiers.

    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
    袿
    -2.67
    鹩
    -2.42
    ⏑
    -2.38
    的那个
    -2.31
    ⚣
    -2.30
    をつけ
    -2.25
    が大
    -2.20
    皝
    -2.20
     are
    -2.19
    hasMoreElements
    -2.19
    POSITIVE LOGITS
    I
    3.34
    \
    3.33
     When
    2.98
    When
    2.89
    If
    2.70
    On
    2.50
    After
    2.45
    As
    2.44
    >
    2.42
    Just
    2.38
    Activations Density 0.007%

    No Known Activations