© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8433
    Prev
    Next
    INDEX
    Explanations

    specific locations and structures

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

    The neuron fires on words that typically appear as components of multiword or hyphenated noun compounds (e.g. “working-class,” “market town,” “woodland,” “needlework,” etc.).

    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
    i
    -1.61
    .
    -1.59
    僥
    -1.42
    -1.38
     successfully
    -1.37
    軋
    -1.35
     eléct
    -1.32
     uží
    -1.30
     frigor
    -1.29
     multiuso
    -1.29
    POSITIVE LOGITS
     setelah
    1.65
     после
    1.62
    rifugal
    1.55
    aragus
    1.55
     این
    1.53
     بعد
    1.52
    ixante
    1.49
     zamiast
    1.45
     cualquier
    1.41
     う
    1.40
    Activations Density 0.155%
    No Known Activations