© 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. 10-GEMMASCOPE-RES-131K
    7. 9149
    Prev
    Next
    INDEX
    Explanations

    region

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

    The neuron fires on occurrences of the word “region” (and its variant “regional”).

    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
    ского
    -2.44
     bluza
    -2.42
     formatos
    -2.41
    衽
    -2.39
    をしました
    -2.30
    🫔
    -2.28
    
    -2.23
    櫈
    -2.23
    trauer
    -2.22
    をしていた
    -2.22
    POSITIVE LOGITS
    n
    3.31
    (
    3.27
    3
    3.08
    E
    2.84
    «
    2.81
    d
    2.72
     ''
    2.69
    m
    2.66
    t
    2.64
    –
    2.56
    Activations Density 0.023%

    No Known Activations