© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 41333
    Prev
    Next
    INDEX
    Explanations

    allows opportunity

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

    The neuron fires on nouns that express positive benefits or potentials (like “opportunity,” “flexibility,” “precision”) often followed by an infinitive, marking promotional or advantageous language.

    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
     inversiones
    -1.66
    ネ
    -1.63
     gracioso
    -1.63
     it
    -1.59
     rígido
    -1.55
     our
    -1.55
     mejoras
    -1.51
     меч
    -1.48
    鄄
    -1.45
     colorida
    -1.43
    POSITIVE LOGITS
     to
    2.14
    5
    2.11
    at
    2.03
    3
    2.02
    are
    1.93
    on
    1.91
    8
    1.83
    4
    1.80
    6
    1.77
    7
    1.77
    Activations Density 0.011%

    No Known Activations