© 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. 10-GEMMASCOPE-RES-131K
    7. 41808
    Prev
    Next
    INDEX
    Explanations

    core file paths

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

    The neuron fires on occurrences of the token “core,” especially in import or package paths (e.g. “processing.core…”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    鲞
    -2.33
    虓
    -2.27
    сны
    -2.14
    訁
    -2.11
     花纹
    -2.11
    嘥
    -2.09
    🫃
    -2.09
    谖
    -2.08
     contribuir
    -2.05
     trzech
    -2.03
    POSITIVE LOGITS
    K
    2.44
    G
    2.34
    ()
    2.27
    B
    2.23
     effortlessly
    2.19
    R
    2.16
    //
    2.14
    ꠥ
    2.14
    M
    2.11
    P
    2.03
    Activations Density 0.017%

    No Known Activations