© 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. 34-GEMMASCOPE-RES-131K
    7. 55699
    Prev
    Next
    INDEX
    Explanations

    attachment theory/somatic marker hypothesis

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

    academic frameworks or theoretical concepts.

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

    This neuron fires strongly on document-structural headings and titles (e.g. section or subsection names) rather than on running text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     JUDGMENT
    -0.76
     payments
    -0.74
    ッピング
    -0.71
    🥾
    -0.70
    quettes
    -0.69
     pembayaran
    -0.69
    semantics
    -0.68
    entir
    -0.68
    Makefile
    -0.68
     Distillery
    -0.68
    POSITIVE LOGITS
     theory
    4.19
     theories
    3.81
     Theory
    2.97
     теории
    2.92
    Theory
    2.78
     théorie
    2.77
    theory
    2.77
     teoría
    2.72
     THEORY
    2.67
     Theories
    2.59
    Activations Density 0.090%

    No Known Activations