© 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. 10-GEMMASCOPE-RES-131K
    4. 130351
    Prev
    Next
    INDEX
    Explanations

    small quantity, part, number, bit

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

    The neuron responds to the word “small” (and its Chinese equivalent 小), flagging that size-indicating descriptor.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    -2.23
     If
    -2.20
    (
    -2.19
     which
    -2.00
     Where
    -1.99
     It
    -1.92
     Since
    -1.91
     With
    -1.90
     When
    -1.86
     How
    -1.78
    POSITIVE LOGITS
     bolsillos
    2.13
    ܆
    2.11
    ₶
    2.08
    躄
    2.05
    bzw
    1.96
     большинстве
    1.96
    ՚
    1.94
    
    1.93
     аккура
    1.92
    куртка
    1.91
    Activations Density 0.004%

    No Known Activations