© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 33353
    Prev
    Next
    INDEX
    Explanations

    android, forgotten password, hire top, chelsea trio

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

    The neuron fires on tokens that contain digits—i.e. numeric literals or any token with numbers embedded in it.

    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
     will
    -0.87
     unrelenting
    -0.86
     remarkable
    -0.85
     decided
    -0.85
     dazzling
    -0.84
    Loai
    -0.84
     relating
    -0.84
     spurred
    -0.83
     talked
    -0.83
     taking
    -0.83
    POSITIVE LOGITS
     DENSITY
    1.01
     FEMALE
    0.93
    currencies
    0.92
     globe
    0.92
    licator
    0.91
    book
    0.90
     венти
    0.88
     souvent
    0.88
     регули
    0.88
     document
    0.87
    Activations Density 0.005%

    No Known Activations