© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85898
    Prev
    Next
    INDEX
    Explanations

    development and progress

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

    The main thing this neuron does is detect mentions of “development” and closely related development‐oriented terms.

    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
    媖
    -1.59
    
    -1.53
    xiii
    -1.53
    尨
    -1.52
    檮
    -1.50
    𓁹
    -1.49
     véhic
    -1.48
    普通的
    -1.48
    ्ष
    -1.47
    傒
    -1.46
    POSITIVE LOGITS
     in
    2.03
    3
    1.70
    {
    1.70
     while
    1.69
    4
    1.63
    [
    1.55
     albeit
    1.49
    ’
    1.49
    ↵
    1.41
     for
    1.40
    Activations Density 0.030%

    No Known Activations