© 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. 73918
    Prev
    Next
    INDEX
    Explanations

    sides and ends of things

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

    The neuron activates on mentions of “side” or “sides,” especially in contexts like “either side” or “both sides.”

    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
     and
    -1.59
     time
    -1.38
     all
    -1.35
     more
    -1.32
     or
    -1.27
     that
    -1.27
    irá
    -1.19
     if
    -1.17
     while
    -1.17
    jenige
    -1.15
    POSITIVE LOGITS
     of
    2.14
     jovem
    1.41
    ༀ
    1.30
     เปิด
    1.24
     แต่
    1.23
    бурге
    1.20
     pienso
    1.20
     facilita
    1.19
     pequeno
    1.16
    ଃ
    1.16
    Activations Density 0.025%

    No Known Activations