© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130436
    Prev
    Next
    INDEX
    Explanations

    The neuron is triggered by tokens containing digits—that is, it picks out numbers (dates, quantities, IDs, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    This is a card

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     minutter
    -1.15
    antart
    -1.10
    媲
    -1.05
    vaného
    -1.02
    jusqu
    -1.01
     incomplète
    -1.00
     balon
    -0.94
     köpa
    -0.93
    annte
    -0.91
    removeFrom
    -0.91
    POSITIVE LOGITS
    <strong>
    1.09
     the
    1.02
     —
    0.91
    スペシャル
    0.87
    Aggi
    0.85
     you
    0.85
    <b>
    0.85
     возможности
    0.84
    给我们
    0.84
     below
    0.83
    Activations Density 0.064%

    No Known Activations