© 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. 54055
    Prev
    Next
    INDEX
    Explanations

    public relations

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

    The neuron is keyed to mentions of public‐relations/PR terminology (e.g. “public,” “relations,” “Communications,” PR agencies, etc.).

    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
     ekos
    -0.71
    şağı
    -0.68
    வு
    -0.66
    trze
    -0.66
    laşı
    -0.65
    Nepal
    -0.65
    中村
    -0.65
    IFFS
    -0.64
    ورد
    -0.63
     murale
    -0.63
    POSITIVE LOGITS
     PR
    5.94
    PR
    4.88
     pr
    2.88
    pr
    2.88
     communications
    2.39
     publicity
    2.39
     press
    2.31
    広報
    2.27
     marketing
    2.19
     пресс
    2.05
    Activations Density 0.095%

    No Known Activations