© 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. 130182
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on nouns that name settings or venues (places or contexts where something happens).

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

    locations or contexts

    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
    >"+
    -1.06
     into
    -1.04
    bodyParser
    -1.03
    を買う
    -1.03
     позволяет
    -1.03
     nélk
    -1.02
    einer
    -1.02
    ۠
    -1.00
    char
    -0.99
    wurde
    -0.97
    POSITIVE LOGITS
     by
    1.23
    での
    1.09
     maupun
    1.08
     during
    1.03
    jeu
    1.02
     lẫn
    1.01
     Behör
    0.93
    airy
    0.89
     любого
    0.87
    deren
    0.86
    Activations Density 0.060%

    No Known Activations