© 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. 2098
    Prev
    Next
    INDEX
    Explanations

    names after prepositions

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

    The neuron is tuned to detect numeric expressions—digits, numbers, and statistical figures—in the text.

    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
    odore
    -0.82
    爆炸
    -0.82
    őle
    -0.81
    Stanford
    -0.81
    Pun
    -0.79
     chaînes
    -0.79
    jiri
    -0.78
    刑
    -0.76
    管
    -0.75
    托
    -0.75
    POSITIVE LOGITS
     Samsung
    1.49
     insurance
    1.32
     Honda
    1.23
     Visa
    1.22
     Huawei
    1.17
     Coca
    1.15
    仕方ない
    1.13
     Verizon
    1.13
     Chevrolet
    1.10
     Toyota
    1.09
    Activations Density 0.070%

    No Known Activations