© 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. 10-GEMMASCOPE-RES-131K
    7. 14740
    Prev
    Next
    INDEX
    Explanations

    structural components and systems

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

    This neuron detects content words in formal academic titles or section headings.

    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
     Angleterre
    -1.41
     emballage
    -1.34
    一阵
    -1.30
     TOXIC
    -1.29
     ajustable
    -1.29
     avenir
    -1.28
     taxe
    -1.28
    ಠ
    -1.27
     Espagne
    -1.26
     vendredi
    -1.25
    POSITIVE LOGITS
     when
    1.71
     or
    1.71
     cuando
    1.46
     когда
    1.40
     people
    1.37
     existing
    1.36
     could
    1.35
    党员
    1.32
     quando
    1.29
     ketika
    1.28
    Activations Density 1.341%

    No Known Activations