© 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. 22-GEMMASCOPE-RES-131K
    4. 67471
    Prev
    Next
    INDEX
    Explanations

    thirtieth anniversary

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

    The neuron activates on mentions of formal meetings or conferences (e.g., “addressed a stakeholders meeting held recently…”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     الشاشة
    -1.16
    を使って
    -1.15
     beijo
    -1.12
     можливо
    -1.09
     både
    -1.06
     eccl
    -1.05
     abraço
    -1.02
     trattano
    -1.02
     обстоятельства
    -1.02
    どれも
    -1.02
    POSITIVE LOGITS
     of
    1.12
    펴
    1.10
     at
    1.10
    кл
    1.06
     escribiendo
    1.05
    ִּ
    1.02
     and
    0.99
     leyendo
    0.97
     fourth
    0.97
     on
    0.97
    Activations Density 0.026%

    No Known Activations