© 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. 55625
    Prev
    Next
    INDEX
    Explanations

    "this software" and "associated"

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

    The neuron is looking for numeric tokens (e.g. version numbers, build numbers, or other digit‐based literals) in the document.

    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
    eningen
    -0.74
     emerged
    -0.72
    țion
    -0.71
    惠
    -0.70
     asunder
    -0.69
    펩
    -0.69
    peng
    -0.68
    França
    -0.67
    annotation
    -0.65
    Firestore
    -0.65
    POSITIVE LOGITS
    dox
    0.79
     nouveaux
    0.73
    CPM
    0.68
    익
    0.68
    トンネル
    0.68
     мара
    0.67
     Compte
    0.66
    upassen
    0.65
     Buscar
    0.64
    odorante
    0.64
    Activations Density 0.043%

    No Known Activations