© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 537
    Prev
    Next
    INDEX
    Explanations

    rescue and aid

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

    The neuron detects numeric tokens (strings of digits) in the text.

    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
     към
    -0.92
     to
    -0.88
    dieran
    -0.81
    到
    -0.75
     đến
    -0.74
    pinas
    -0.73
    ープ
    -0.72
    ፤
    -0.72
     kepada
    -0.69
     captioned
    -0.69
    POSITIVE LOGITS
     rescue
    3.95
     aid
    3.22
    rescue
    3.11
    Rescue
    2.69
     Rescue
    2.69
     assistance
    2.47
     rescues
    2.06
    Aid
    2.02
     помощь
    1.99
     Aid
    1.98
    Activations Density 0.025%

    No Known Activations