© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 12819
    Prev
    Next
    INDEX
    Explanations

    strategy, procedure, protocol

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

    The neuron identifies terms that introduce or refer to research methods or strategies (e.g., “strategy,” “procedure,” “methodology”).

    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
     their
    -1.77
    pulseira
    -1.57
    这里
    -1.56
     berühm
    -1.52
    。】
    -1.44
    賅
    -1.43
    ㎏
    -1.42
    *;
    -1.40
    joyed
    -1.39
     trovano
    -1.38
    POSITIVE LOGITS
    ed
    1.93
     auch
    1.70
     anche
    1.64
    せよ
    1.58
     to
    1.48
    噲
    1.48
    .”
    1.45
     of
    1.45
    atario
    1.44
    快要
    1.44
    Activations Density 0.088%

    No Known Activations