© 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. 22-GEMMASCOPE-RES-131K
    7. 27744
    Prev
    Next
    INDEX
    Explanations

    transportation and transfer services

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

    The neuron fires on mentions of transportation or logistical services (e.g. shuttle, transfer/pick-up, luggage storage, delivery/assistance).

    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
     .
    -1.17
     m
    -1.09
     
    -1.05
    mathrm
    -1.04
     it
    -1.02
    つも
    -1.02
     возможность
    -0.99
     use
    -0.98
     results
    -0.97
     increase
    -0.97
    POSITIVE LOGITS
    
    1.21
    EUROPE
    1.20
    jahres
    1.16
     from
    1.16
    пель
    1.14
     évé
    1.13
    rions
    1.13
     reposo
    1.12
     verbinding
    1.12
     vérit
    1.12
    Activations Density 0.005%

    No Known Activations