© 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. 2407
    Prev
    Next
    INDEX
    Explanations

    numbers and words

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

    The neuron fires strongly for numeric tokens (digits or multi‐digit numbers).

    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
    TEMPO
    -0.88
     bữa
    -0.85
     gepub
    -0.82
     perturbations
    -0.82
    keiten
    -0.82
    ností
    -0.82
    volvo
    -0.82
    gucci
    -0.82
    Сле
    -0.81
    bieten
    -0.81
    POSITIVE LOGITS
    oci
    0.93
     zero
    0.90
    Zero
    0.80
    zero
    0.80
    4
    0.78
    などが
    0.77
    8
    0.77
    3
    0.76
    6
    0.76
    media
    0.76
    Activations Density 0.042%

    No Known Activations