© 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. 87109
    Prev
    Next
    INDEX
    Explanations

    SEMA Show, Air India, Q:

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

    The neuron is specifically detecting occurrences of the three-digit number “100.”

    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
    addPreferredGap
    -1.16
     pitää
    -1.03
     ListItem
    -0.96
    apnews
    -0.94
     pengantin
    -0.92
    grunns
    -0.88
     viera
    -0.85
    dailymail
    -0.84
    cnbc
    -0.84
     lelaki
    -0.83
    POSITIVE LOGITS
    addContainerGap
    1.59
    Ignore
    0.96
    ющем
    0.87
     ignore
    0.85
    ื
    0.81
     ZERO
    0.80
    ignore
    0.79
     Ignore
    0.78
    Zero
    0.75
     новую
    0.75
    Activations Density 0.000%

    No Known Activations