© 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. 22-GEMMASCOPE-RES-131K
    7. 70890
    Prev
    Next
    INDEX
    Explanations

    transport station names

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

    The neuron strongly activates on mentions of transit “stations” (train, subway, or rail stops) and related location‐describing phrases.

    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
    ษัท
    -1.37
     vermittelt
    -1.23
    COMES
    -1.22
    lateinit
    -1.20
    ologous
    -1.14
    θεί
    -1.14
     putem
    -1.14
     beweisen
    -1.14
    maken
    -1.13
    țiuni
    -1.13
    POSITIVE LOGITS
     on
    1.81
     dormitórios
    1.34
     elevador
    1.27
     betrek
    1.24
    艏
    1.18
     dormitorios
    1.17
     пони
    1.10
     adjacent
    1.10
     operadores
    1.10
    hely
    1.09
    Activations Density 0.071%

    No Known Activations