© 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. 22-GEMMASCOPE-RES-131K
    7. 71150
    Prev
    Next
    INDEX
    Explanations

    concepts followed by modifiers

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

    The neuron fires on consecutive token pairs that form fixed or technical collocations (two‐word noun or phrase compounds).

    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
     élégante
    -0.85
     heureuse
    -0.84
    uxe
    -0.80
    лио
    -0.80
    dropIfExists
    -0.79
     Konrad
    -0.79
     նաև
    -0.78
     hoppas
    -0.77
     جشن
    -0.77
    JButton
    -0.76
    POSITIVE LOGITS
    isDead
    0.86
    scaleX
    0.82
     correctly
    0.77
    jau
    0.75
     pars
    0.74
    Peers
    0.73
    travis
    0.73
    rental
    0.73
     difficulties
    0.72
    /;
    0.71
    Activations Density 0.196%

    No Known Activations