© 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. 66199
    Prev
    Next
    INDEX
    Explanations

    codes and numbers

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

    The neuron strongly activates on numeric tokens—i.e. sequences of digits such as phone numbers, IDs, years, DOI numbers, etc.

    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
     Hügel
    -0.88
     typical
    -0.88
     no
    -0.88
     your
    -0.88
     rare
    -0.86
     this
    -0.85
     Frühling
    -0.85
     mụn
    -0.85
    ﹶ
    -0.84
     now
    -0.84
    POSITIVE LOGITS
     Balkans
    0.91
     fasteners
    0.87
    式的
    0.85
     Là
    0.85
     slippers
    0.85
    CBC
    0.85
    endu
    0.84
    Helena
    0.84
    Spells
    0.83
    āk
    0.82
    Activations Density 0.015%

    No Known Activations