© 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. 161
    Prev
    Next
    INDEX
    Explanations

    he has, when they, blessed by

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

    This neuron fires strongly on tokens that occur right at the start of a new text segment (i.e. the first real word or letter opening each block).

    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
    今朝
    -1.02
     for
    -1.00
     epitom
    -0.93
     Elsewhere
    -0.92
    Elsewhere
    -0.92
     their
    -0.92
     onderdeel
    -0.92
     menerapkan
    -0.90
      「
    -0.90
    шники
    -0.90
    POSITIVE LOGITS
     внеш
    1.02
    などが
    1.00
    different
    1.00
     realmente
    0.97
    asilkan
    0.97
     fiecare
    0.94
    UL
    0.93
    ১
    0.92
     이미지
    0.91
    각
    0.91
    Activations Density 0.010%

    No Known Activations