© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 83085
    Prev
    Next
    INDEX
    Explanations

    expressions of love and enjoyment

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

    The neuron strongly activates on personal and interrogative pronouns (e.g. I, my, she, he, who, what), i.e. words that refer directly to people or pose questions.

    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
    znej
    -0.94
    hasMany
    -0.91
     грамм
    -0.87
     бампер
    -0.86
     desirable
    -0.86
    φαλ
    -0.85
    ικα
    -0.82
    lden
    -0.82
    redirects
    -0.80
     schön
    -0.79
    POSITIVE LOGITS
     love
    5.94
     loves
    4.31
     LOVE
    3.70
    love
    3.69
    Love
    3.61
     Love
    3.56
     loved
    3.41
    LOVE
    3.34
    爱
    2.81
     любовь
    2.78
    Activations Density 0.114%

    No Known Activations