© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129115
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on numeric tokens and their surrounding punctuation—i.e. digits, slashes, hyphens, underscores, etc.—as used in section numbers, timestamps, IDs, or file‐path–style references.

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

    section references

    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
     its
    -1.27
     türkiye
    -1.21
    💃
    -1.05
     from
    -1.03
    ваете
    -1.02
     to
    -1.00
     norske
    -0.99
    」(
    -0.98
    räck
    -0.98
    🗑
    -0.97
    POSITIVE LOGITS
     connessione
    1.08
    参考にして
    1.07
    了下去
    1.06
     collegamento
    1.05
    chy
    1.05
    ara
    1.05
    ro
    1.03
    Problemas
    1.02
     immediately
    1.01
    了下来
    1.01
    Activations Density 0.001%

    No Known Activations