© 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. 86803
    Prev
    Next
    INDEX
    Explanations

    visiting family or friends

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

    The neuron is detecting references to “visit” (in any tense or form, often paired with “with” or context words).

    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
    ↵
    -1.63
     enseñanza
    -1.63
     häufigsten
    -1.55
     personalización
    -1.53
     to
    -1.52
     a
    -1.51
    lgari
    -1.51
     innovación
    -1.48
     navegación
    -1.48
     comprensión
    -1.45
    POSITIVE LOGITS
    if
    1.59
    when
    1.59
    0
    1.53
     with
    1.49
    ณ์
    1.45
    upon
    1.45
    It
    1.45
    ments
    1.43
    ’;
    1.39
    able
    1.37
    Activations Density 0.010%

    No Known Activations