© 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. 92185
    Prev
    Next
    INDEX
    Explanations

    session plan or package deal

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

    The neuron fires on words naming conference or meeting events and their organization/scheduling (e.g. sessions, symposia, program, field trips, annual meeting).

    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
     detective
    -0.72
    種の
    -0.68
    回调
    -0.67
     Normalized
    -0.66
    Tazama
    -0.66
     Tablet
    -0.66
     Todo
    -0.66
    month
    -0.65
     Speaking
    -0.65
    stasi
    -0.65
    POSITIVE LOGITS
     session
    2.39
     Session
    2.17
    Session
    1.99
     sessions
    1.88
    session
    1.88
    SESSION
    1.85
     SESSION
    1.55
     Sessions
    1.46
     sesiones
    1.38
    Sessions
    1.34
    Activations Density 0.018%

    No Known Activations