© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 100285
    Prev
    Next
    INDEX
    Explanations

    house plans, car insurance, card loans

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

    This neuron activates on prominent commercial or service‐offering headings or keywords (e.g. “Escort Service,” “Live Streaming,” “Birthday Cake,” “Floor Plans,” “Debit Card Loans,” 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
     dát
    -1.46
     baterías
    -1.45
    astie
    -1.42
     pestañas
    -1.36
     tasas
    -1.35
    Cependant
    -1.35
    ösen
    -1.34
     ktoré
    -1.34
    jenigen
    -1.32
    př
    -1.32
    POSITIVE LOGITS
     in
    2.56
     of
    1.67
     for
    1.54
     so
    1.38
     since
    1.29
     this
    1.23
    Many
    1.23
    Since
    1.22
     do
    1.19
     Since
    1.15
    Activations Density 0.268%

    No Known Activations