© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16200
    Prev
    Next
    INDEX
    Explanations

    highlighting specific aspects

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

    The neuron detects discourse markers (like “emphasis,” “focus,” or “special attention”) that signal a highlighted topic or emphasis in academic writing.

    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
     another
    -1.21
     esfuerzan
    -1.20
     fleste
    -1.09
    鷙
    -1.07
    aneity
    -1.06
    纯粹
    -1.06
    确实是
    -1.05
    慤
    -1.05
    踰
    -1.04
    自体は
    -1.03
    POSITIVE LOGITS
     особенно
    1.52
     insbesondere
    1.43
    particularly
    1.34
     особли
    1.34
    特に
    1.26
    especially
    1.25
     aquellos
    1.20
     besonders
    1.20
    specifically
    1.19
     particularly
    1.17
    Activations Density 0.090%

    No Known Activations