© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99091
    Prev
    Next
    INDEX
    Explanations

    internal contexts

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

    The neuron fires on occurrences of the identifier “internal” (e.g. in module, package, import, or path names).

    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
    
    -2.66
     keď
    -2.61
    𖣔
    -2.58
    🫅
    -2.53
    鹜
    -2.50
    archiwizowane
    -2.48
    籥
    -2.47
    都知道
    -2.42
    釙
    -2.42
    sistors
    -2.34
    POSITIVE LOGITS
    ization
    3.45
    for
    3.13
    3
    3.05
    𓆜
    3.03
    1
    2.98
    趼
    2.95
    7
    2.92
    this
    2.91
    地说道
    2.88
    6
    2.80
    Activations Density 0.018%

    No Known Activations