© 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. 69205
    Prev
    Next
    INDEX
    Explanations

    Common introductory words

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

    The neuron strongly activates on common English introductory phrases—especially the sequence “This is a.”

    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
    ขอบคุณ
    -1.59
    tarta
    -1.59
     navide
    -1.58
    <bos>
    -1.53
     his
    -1.49
     그의
    -1.48
    และ
    -1.47
     그것
    -1.46
    ρούν
    -1.40
     podoba
    -1.38
    POSITIVE LOGITS
     This
    2.00
    n
    1.90
     If
    1.75
     will
    1.73
    u
    1.65
    t
    1.59
    d
    1.56
    v
    1.55
     to
    1.53
    a
    1.52
    Activations Density 0.034%

    No Known Activations