© 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. 86819
    Prev
    Next
    INDEX
    Explanations

    presentation or talk

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

    The neuron activates on mentions of slide‐based presentations (e.g. “PowerPoint,” “presentation(s),” “slide”).

    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
     опубли
    -0.75
     série
    -0.71
    /+
    -0.71
    ghalaya
    -0.71
    LING
    -0.69
    commodation
    -0.69
    пак
    -0.68
    ∥
    -0.67
    putc
    -0.67
    nige
    -0.66
    POSITIVE LOGITS
     presentation
    4.16
     presentations
    3.80
    presentation
    3.06
    Presentation
    2.86
     Presentations
    2.83
     Presentation
    2.72
     презента
    2.61
     PRESENTATION
    2.52
    Presentations
    2.47
     présentation
    2.45
    Activations Density 0.044%

    No Known Activations