© 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. 119016
    Prev
    Next
    INDEX
    Explanations

    travel agents, occasions, advice

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

    The neuron consistently fires on the word “travel” (especially as a category or section label), marking instances of the term in headings or tags.

    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
    '
    -5.88
    ‘
    -3.05
    \
    -2.97
    肏
    -2.44
    –
    -2.34
     —
    -2.30
    颪
    -2.28
            
    -2.25
    ();
    -2.20
     proviene
    -2.16
    POSITIVE LOGITS
    e
    3.14
    ဴ
    3.02
    婞
    3.00
    a
    2.88
    谞
    2.70
    了一个
    2.64
    ㉕
    2.52
    ၞ
    2.50
    नलोड
    2.48
    ༑
    2.47
    Activations Density 0.010%

    No Known Activations