© 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. 34-GEMMASCOPE-RES-131K
    4. 23632
    Prev
    Next
    INDEX
    Explanations

    cruiser Prinz Eugen Kaiyo Maru Diglyceride May I

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

    The neuron fires strongly on numeric expressions (digits or spelled-out numerals) in technical or specification contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Infantry
    -0.87
     infantry
    -0.81
     soldier
    -0.80
     military
    -0.77
     army
    -0.76
    Army
    -0.76
     Zutaten
    -0.75
    dagogik
    -0.75
    brück
    -0.73
    lyn
    -0.72
    POSITIVE LOGITS
     concealment
    0.86
     Samar
    0.75
    inals
    0.72
    分组
    0.72
    กิน
    0.72
    NOPQRST
    0.69
    袭
    0.67
    ENIX
    0.66
     CAP
    0.66
     Southwest
    0.66
    Activations Density 0.011%

    No Known Activations