© 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. 10-GEMMASCOPE-RES-131K
    7. 120035
    Prev
    Next
    INDEX
    Explanations

    making more intense

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

    The neuron fires on words that express an increase in intensity or degree (e.g. “intensified,” “heightened,” “intensifying”).

    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
    廕
    -2.72
    embro
    -2.36
    勦
    -2.36
    ′,
    -2.36
    肫
    -2.27
     gydy
    -2.25
     estrateg
    -2.25
    啻
    -2.23
    ⸫
    -2.20
     íntegra
    -2.19
    POSITIVE LOGITS
    d
    3.31
    1
    3.17
     =
    2.92
    6
    2.81
    ?"
    2.81
    3
    2.66
    f
    2.64
    7
    2.63
    4
    2.44
    自己
    2.42
    Activations Density 0.004%

    No Known Activations