© 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. 105535
    Prev
    Next
    INDEX
    Explanations

    provide information or guidance

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

    The main thing this neuron does is detect the verb “inform.”

    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
    蹰
    -3.09
     '
    -2.48
     In
    -2.44
    形状
    -2.38
    на
    -2.28
     somber
    -2.11
     
    -2.08
     mencionado
    -2.03
     "'
    -2.02
    тесь
    -2.00
    POSITIVE LOGITS
    .
    2.91
    袮
    2.67
    戋
    2.67
    猡
    2.56
    .")
    2.55
     itſelf
    2.44
    垆
    2.44
    我们要
    2.44
     estekak
    2.39
    涐
    2.39
    Activations Density 0.002%

    No Known Activations