© 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. 22-GEMMASCOPE-RES-131K
    7. 39352
    Prev
    Next
    INDEX
    Explanations

    rate, times, today

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

    The neuron is a “frequency detector” that flags very common high‐frequency words (e.g. frequent function words and other highly common tokens).

    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
    ⽰
    -1.06
     izan
    -1.02
     maillot
    -1.00
     nampak
    -0.98
    omena
    -0.98
     menyen
    -0.95
     gibi
    -0.95
    如图
    -0.94
     있습니다
    -0.93
     berge
    -0.93
    POSITIVE LOGITS
     would
    1.50
     it
    1.45
     should
    1.44
     likely
    1.34
     could
    1.32
     any
    1.30
     shouldn
    1.22
     poderia
    1.20
     anyone
    1.19
     wouldn
    1.19
    Activations Density 0.042%

    No Known Activations