© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130179
    Prev
    Next
    INDEX
    Explanations

    National Wildlife Refuge

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

    scientific or technical terms with suffixes like 'in', 'ins', or geographical locations including National Wildlife Refuge.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron responds to tokens ending in the suffix “in.”

    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
    〼
    -1.33
    ⒋
    -1.31
    媄
    -1.30
    
    -1.27
     precedenti
    -1.26
     Miß
    -1.25
    oczes
    -1.20
     Joaqu
    -1.20
     ہیں
    -1.18
    ꯶
    -1.18
    POSITIVE LOGITS
     naszych
    1.38
    特有
    1.33
     інших
    1.30
    大约
    1.21
    ༈
    1.20
    ту
    1.20
     that
    1.18
     минимум
    1.17
    乃至
    1.17
     about
    1.16
    Activations Density 0.011%

    No Known Activations