© 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. 34-GEMMASCOPE-RES-131K
    7. 115903
    Prev
    Next
    INDEX
    Explanations

    opens new possibilities

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

    The neuron activates on specialized scientific or technical terms (highly domain-specific nouns and 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
    글
    -0.82
    📵
    -0.81
    suchen
    -0.77
    を防
    -0.77
     يقوم
    -0.76
    ₽
    -0.75
    sieht
    -0.73
    cach
    -0.73
    pasang
    -0.71
    setItems
    -0.71
    POSITIVE LOGITS
     opens
    5.06
     opening
    4.84
     opened
    4.47
    Opening
    3.94
    opening
    3.80
     Opening
    3.75
     mở
    3.66
    opens
    3.63
     Opens
    3.50
     abrir
    3.30
    Activations Density 0.165%

    No Known Activations