© 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. 84284
    Prev
    Next
    INDEX
    Explanations

    numbers and academic journals

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

    The neuron detects long sequences of digits or numeric identifiers (e.g. ISSN numbers, years, and similar multi‐digit codes).

    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
    athers
    -1.16
     COME
    -0.89
     molti
    -0.88
     approfon
    -0.87
    viated
    -0.85
    nius
    -0.85
     molte
    -0.84
     leak
    -0.84
    assins
    -0.84
    isamment
    -0.82
    POSITIVE LOGITS
     中央
    0.80
     alcalde
    0.79
     hivyo
    0.77
     egyéb
    0.76
     bringing
    0.75
    squareup
    0.75
     primarily
    0.75
     Print
    0.75
     put
    0.74
    nadores
    0.74
    Activations Density 0.005%

    No Known Activations