© 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. 75769
    Prev
    Next
    INDEX
    Explanations

    accept or reject request

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

    The neuron specializes in spotting numeric tokens (digits or number-like literals) throughout 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
    ⇐
    -1.08
    declared
    -1.02
    btnLogin
    -0.94
     europa
    -0.89
     perpé
    -0.88
     honn
    -0.88
     paulo
    -0.88
     licen
    -0.87
    Guaranteed
    -0.87
     absolut
    -0.86
    POSITIVE LOGITS
     accept
    2.55
     acceptance
    2.33
     accepted
    2.28
     reject
    2.27
     rejected
    2.20
     rejection
    2.14
     accepting
    2.02
     declined
    1.98
     Accept
    1.98
     request
    1.84
    Activations Density 0.016%

    No Known Activations