© 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. 22-GEMMASCOPE-RES-131K
    7. 27999
    Prev
    Next
    INDEX
    Explanations

    business or financial activity

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

    The neuron fires on the main event words (the core verb or head noun) that carry a clause’s primary action or subject.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     varias
    -1.09
     durch
    -1.04
    дек
    -1.00
    dicionado
    -1.00
     mehrere
    -0.99
    Opens
    -0.96
     jezik
    -0.95
    上がる
    -0.94
     उन्ह
    -0.93
    unakan
    -0.92
    POSITIVE LOGITS
     защото
    1.18
     also
    1.16
     آمریک
    1.12
    ?
    0.92
     education
    0.92
    を見ると
    0.91
     Portanto
    0.91
     ajoutez
    0.91
     normaux
    0.90
     kuitenkin
    0.89
    Activations Density 0.003%

    No Known Activations