© 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. 22-GEMMASCOPE-RES-131K
    7. 34931
    Prev
    Next
    INDEX
    Explanations

    html code generation

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

    The neuron fires on numeric literals (i.e. multi-digit numbers) in the code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    0
    -1.11
     to
    -1.07
     щодо
    -1.06
    2
    -0.98
     любы
    -0.98
    地说道
    -0.95
    XCTAssert
    -0.95
    so
    -0.94
     джере
    -0.93
     большин
    -0.93
    POSITIVE LOGITS
    ﻹ
    1.16
    appendTo
    1.15
    ﻷ
    1.13
     mereka
    1.07
     html
    1.05
     previa
    1.01
    zeniem
    1.01
    mpty
    1.01
    ')).
    1.00
     new
    1.00
    Activations Density 0.009%

    No Known Activations