© 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. 4294
    Prev
    Next
    INDEX
    Explanations

    background, Q, Reference, We

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

    The neuron specializes in spotting individual digits and related punctuation within numeric identifiers (e.g., DOIs, version numbers, dates).

    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
    agosto
    -1.01
     allerede
    -0.97
     in
    -0.96
     all
    -0.96
     already
    -0.95
     more
    -0.93
     after
    -0.92
    કો
    -0.92
     Fittings
    -0.89
     bereits
    -0.89
    POSITIVE LOGITS
    Öffnungszeiten
    1.02
    tasche
    0.97
    每一个
    0.97
    Escrito
    0.96
    Geschäfts
    0.94
     Unterscheidung
    0.93
    Einsatz
    0.93
    Beratung
    0.93
    Achtung
    0.93
    Unsere
    0.93
    Activations Density 0.003%

    No Known Activations