© 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. 129536
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on blocks of text that describe logistical or navigational details—maps, routes, walking directions, accommodation options, points of interest, etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    listings and information

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     internal
    -1.12
     processing
    -1.10
     Bewußt
    -1.01
     process
    -1.00
     plantilla
    -0.99
    姥
    -0.97
     übernahm
    -0.97
     преимущества
    -0.97
    llywood
    -0.96
    Transcriptie
    -0.96
    POSITIVE LOGITS
     listings
    1.25
     information
    1.24
     lokale
    1.21
    情報
    1.13
     recommendations
    1.13
     guide
    1.10
    ϒ
    1.06
    potensi
    1.05
     ratings
    1.03
     informazioni
    1.03
    Activations Density 0.084%

    No Known Activations