© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 86919
    Prev
    Next
    INDEX
    Explanations

    data; );

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

    The neuron fires on method calls that fetch or retrieve data (e.g. HTTP GET/PUT, list, findOne, 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_10/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
     linge
    -1.52
     bombe
    -1.45
     soldat
    -1.44
     tatu
    -1.41
     brune
    -1.40
     goud
    -1.38
     lage
    -1.38
     medis
    -1.38
     maig
    -1.38
     lait
    -1.37
    POSITIVE LOGITS
     öffentlich
    1.51
    :
    1.50
    mberto
    1.47
     öff
    1.36
     they
    1.35
     obecnie
    1.34
     same
    1.28
     such
    1.28
    -
    1.27
     öffentlichen
    1.26
    Activations Density 0.017%

    No Known Activations