© 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. 75445
    Prev
    Next
    INDEX
    Explanations

    citations and identifiers

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

    The neuron fires on long digit sequences (four or more digits in a row), such as the numeric identifiers you see in reference citations.

    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
     and
    -1.99
     ostensibly
    -1.55
     or
    -1.53
     this
    -1.50
     of
    -1.50
     it
    -1.47
     auf
    -1.32
     blatantly
    -1.30
     There
    -1.29
     Also
    -1.27
    POSITIVE LOGITS
    がありますが
    1.73
    んじゃ
    1.66
    igth
    1.64
     BehaviorSubject
    1.53
    があるので
    1.52
    があり
    1.52
    って思
    1.52
     createSlice
    1.52
     ApiService
    1.50
     LoginComponent
    1.48
    Activations Density 0.028%

    No Known Activations