© 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. 34-GEMMASCOPE-RES-131K
    7. 107405
    Prev
    Next
    INDEX
    Explanations

    arb or abor prefix

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

    The neuron activates on words containing the character sequence “arbo” (e.g. arbor, arbovirus).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Jdbc
    -0.70
    opje
    -0.69
    SOME
    -0.68
    '#
    -0.68
    úmer
    -0.68
     jaw
    -0.67
    thunder
    -0.67
    🥕
    -0.67
     asia
    -0.67
     Capac
    -0.66
    POSITIVE LOGITS
    vita
    0.95
     måned
    0.72
    currency
    0.71
    ringar
    0.69
     vitae
    0.68
    感器
    0.68
    氪
    0.68
    ghar
    0.67
    kost
    0.67
    ost
    0.66
    Activations Density 0.036%

    No Known Activations