© 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. 129172
    Prev
    Next
    INDEX
    Explanations

    how it works

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

    This neuron detects phrasing that introduces or labels explanatory sections or questions about how something works (e.g. “How it works,” “How does … work?”).

    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
    粜
    -1.63
     cueva
    -1.59
    uransi
    -1.54
    蟜
    -1.48
    carnated
    -1.48
    EdgeInsets
    -1.45
     refugi
    -1.44
    ༛
    -1.44
    XVIII
    -1.44
     hebben
    -1.44
    POSITIVE LOGITS
    .
    1.95
    x
    1.67
    ”
    1.50
    .)
    1.49
     of
    1.46
    At
    1.41
     where
    1.41
     At
    1.40
    In
    1.38
     today
    1.36
    Activations Density 0.048%

    No Known Activations