© 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. 27981
    Prev
    Next
    INDEX
    Explanations

    start of sentence or phrase

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

    The neuron fires on the conjunction “and” when it’s joining two compass‐direction spatial phrases (e.g. “south of X and southeast of Y”).

    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
     Conférence
    -1.13
     cortina
    -1.11
     its
    -1.10
    ENNE
    -1.08
     tarta
    -1.07
     celta
    -1.07
     gwaran
    -1.07
    렸
    -1.07
    quarelle
    -1.06
     indique
    -1.02
    POSITIVE LOGITS
     непосредственно
    1.15
    IN
    1.12
     befes
    1.10
    ׳
    1.09
    ara
    1.08
     cheminée
    1.07
     ".";
    1.07
    了下去
    1.06
    og
    1.06
    ay
    1.06
    Activations Density 0.000%

    No Known Activations