© 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. 98179
    Prev
    Next
    INDEX
    Explanations

    junctions and intersections

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

    The neuron activates strongly on mentions of road or place junctions/intersections.

    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
     serce
    -1.20
     setembro
    -1.16
    ających
    -1.15
     zwanzig
    -1.15
     aún
    -1.15
     mientras
    -1.15
     letzt
    -1.13
    stacles
    -1.10
     второй
    -1.09
     geführt
    -1.09
    POSITIVE LOGITS
     where
    1.48
     crossroads
    1.26
    Vé
    1.21
     trafik
    1.20
    图源
    1.11
     ');
    1.10
    صبحت
    1.09
     distribuidor
    1.06
    Lưu
    1.05
    Tempat
    1.05
    Activations Density 0.026%

    No Known Activations