© 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. 50506
    Prev
    Next
    INDEX
    Explanations

    URLs and file paths

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

    The neuron activates on numeric tokens—i.e. numbers, years, dataset IDs, reference codes, or other digit sequences.

    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
     just
    -1.09
     at
    -1.00
     before
    -0.95
     with
    -0.85
     on
    -0.85
     any
    -0.84
     innumerable
    -0.83
     ironically
    -0.82
     July
    -0.82
     because
    -0.82
    POSITIVE LOGITS
    asily
    0.97
    ÈRE
    0.95
     bílé
    0.94
    appears
    0.94
    apparently
    0.93
    ANDS
    0.89
    ⠀⠀⠀⠀⠀⠀⠀⠀
    0.88
     لهذه
    0.88
    Ii
    0.86
     DIFFERENT
    0.86
    Activations Density 0.002%

    No Known Activations