© 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. 4410
    Prev
    Next
    INDEX
    Explanations

    navigation and planning

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

    The neuron fires on specialized technical or scientific terminology—especially model names, measurement terms, and navigation‐related jargon.

    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
    gjenge
    -0.82
    ご覧
    -0.77
     Quais
    -0.76
    หว่าง
    -0.72
    classID
    -0.72
     obrazu
    -0.70
     Formato
    -0.70
    根據
    -0.69
    Cham
    -0.69
    てて
    -0.69
    POSITIVE LOGITS
     Navigation
    1.66
     navigation
    1.64
    navigation
    1.50
     tables
    1.30
    Navigation
    1.27
     navigational
    1.21
    nav
    1.17
     navig
    1.17
    计算
    1.16
     calculating
    1.16
    Activations Density 0.028%

    No Known Activations