© 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. 33740
    Prev
    Next
    INDEX
    Explanations

    .com and .org domains

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

    The neuron detects common top‐level domain tokens (e.g. “com”, “org”, “io”) in code identifiers.

    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
     on
    -1.26
     which
    -1.07
    !!
    -1.05
     any
    -1.04
     when
    -1.01
     even
    -1.00
     by
    -0.96
     !!!
    -0.95
     some
    -0.93
    !!!!!
    -0.93
    POSITIVE LOGITS
     unn
    1.06
     angeboten
    1.04
     '-'
    1.04
     mesmerizing
    1.03
     SEVEN
    1.02
     '=',
    1.01
    totally
    1.01
    Ḿ
    0.98
     入り口
    0.98
    AJ
    0.97
    Activations Density 0.010%

    No Known Activations