© 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. 22-GEMMASCOPE-RES-131K
    7. 68797
    Prev
    Next
    INDEX
    Explanations

    emotion, desolation, storm

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

    The neuron is highly activated by standalone numbers or numeric tokens.

    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
     DIAGRAM
    -1.15
     LIBRARIES
    -1.09
     lini
    -1.09
     REDUCTION
    -1.08
     barrio
    -1.06
     INFLUENCE
    -1.04
     rocha
    -1.00
     عنه
    -0.99
     roche
    -0.99
     assum
    -0.99
    POSITIVE LOGITS
     (
    0.93
     reciben
    0.87
     Most
    0.86
    せます
    0.86
     No
    0.86
     stronger
    0.86
     more
    0.85
     getting
    0.84
     Just
    0.84
     for
    0.84
    Activations Density 0.016%

    No Known Activations