© 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. 22-GEMMASCOPE-RES-131K
    4. 28145
    Prev
    Next
    INDEX
    Explanations

    effects and actions

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

    The neuron strongly activates on the formal, content‐heavy vocabulary and phrasing typical of biomedical research abstracts or scientific reports.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     Pilihan
    -1.34
     religieuses
    -1.33
     Terbaru
    -1.27
     prêtres
    -1.27
     Menggunakan
    -1.27
     Eſ
    -1.25
     appris
    -1.18
     chrétien
    -1.18
     Fungsi
    -1.16
     specchio
    -1.16
    POSITIVE LOGITS
     effects
    1.32
     effect
    1.29
     different
    1.29
     target
    1.20
     direct
    1.18
    —
    1.17
     functions
    1.16
     response
    1.16
     th
    1.15
     change
    1.14
    Activations Density 0.305%

    No Known Activations