© 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. 59979
    Prev
    Next
    INDEX
    Explanations

    initials and acronyms

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

    The neuron fires on tokens containing digits—e.g. years, numeric codes, or any number‐containing strings.

    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
    CT
    -0.82
    CM
    -0.81
    CP
    -0.81
    CSS
    -0.80
    ednesday
    -0.79
    CDD
    -0.78
    cka
    -0.77
    CSD
    -0.76
    MathML
    -0.75
     CMR
    -0.74
    POSITIVE LOGITS
     SDC
    1.91
     STC
    1.88
     YC
    1.85
    ZC
    1.80
    YC
    1.79
     ALC
    1.78
     SPC
    1.77
     AFC
    1.76
     MTC
    1.73
     ATC
    1.71
    Activations Density 0.190%

    No Known Activations