© 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. 94192
    Prev
    Next
    INDEX
    Explanations

    social media

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

    The neuron fires strongly on mentions of social media–related terms (e.g. “social,” “media,” “marketing,” “on [a platform]”), effectively detecting references to social networking and its marketing context.

    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
    cheme
    -0.75
    quitos
    -0.73
     خدمة
    -0.73
    reiches
    -0.72
    foods
    -0.72
    的上
    -0.71
    ideon
    -0.71
     Scheme
    -0.71
    atro
    -0.71
    naf
    -0.70
    POSITIVE LOGITS
     social
    5.44
    social
    3.86
    Social
    3.63
     Social
    3.50
    社交
    3.05
    SOCIAL
    2.98
     SOCIAL
    2.98
     socials
    2.73
     sosyal
    2.73
     sosial
    2.69
    Activations Density 0.055%

    No Known Activations