© 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. 129347
    Prev
    Next
    INDEX
    Explanations

    very, very intensifiers

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

    The neuron is keyed to strong degree-adverbs—especially the intensifier “very.”

    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
     بعضی
    -1.45
    still
    -1.38
     wszyst
    -1.36
     bezit
    -1.35
     которые
    -1.34
     which
    -1.33
     protege
    -1.31
     algunas
    -1.31
     protégé
    -1.29
     algumas
    -1.27
    POSITIVE LOGITS
    TextEditing
    1.27
     '/':
    1.24
     tecnológico
    1.20
     rowspan
    1.18
    ">(</
    1.17
    刘
    1.13
     cuidad
    1.13
     contento
    1.12
     efectivo
    1.12
     colspan
    1.10
    Activations Density 0.053%

    No Known Activations