© 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. 67705
    Prev
    Next
    INDEX
    Explanations

    U.S. Pat. No

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

    This neuron fires on the digit “3,” especially when it appears as part of patent or document identification numbers.

    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
    ,
    -1.30
    $
    -1.27
    "
    -1.19
    +='
    -1.13
    0
    -1.13
    \
    -1.05
    "'
    -1.05
    +
    -1.04
     agences
    -1.02
    </h3>
    -1.01
    POSITIVE LOGITS
    焄
    1.18
    瑧
    1.11
    Ruj
    1.07
    IQUES
    1.07
    配送
    1.05
    بسم
    1.05
    BACA
    1.04
    出来ました
    1.04
    hlte
    1.03
    Organizador
    1.03
    Activations Density 0.036%

    No Known Activations