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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 90631
    Prev
    Next
    INDEX
    Explanations

    services and amenities

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

    The neuron primarily activates on numeric tokens—standalone numbers or digits that denote quantities, distances, counts, 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_34/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
    núť
    -0.91
     Karte
    -0.86
    ">)</
    -0.85
    kadot
    -0.85
    FieldOffsetTable
    -0.83
    燜
    -0.83
    虽然
    -0.82
    纳
    -0.82
    MMA
    -0.81
    GRA
    -0.80
    POSITIVE LOGITS
     fax
    1.25
     Internet
    1.22
     computers
    1.20
     computer
    1.19
     internet
    1.12
     Wi
    1.05
     Fax
    1.03
     notary
    1.03
     ample
    1.02
     telephone
    0.99
    Activations Density 0.029%

    No Known Activations