© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 45269
    Prev
    Next
    INDEX
    Explanations

    nocturnal or terminal sequences

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

    The neuron is keyed to spotting occurrences of the word “nocturnal.”

    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
     anún
    -2.48
    ⢊
    -2.42
    ﭽ
    -2.34
     ある
    -2.30
     стал
    -2.25
    AutoresizingMask
    -2.23
     enjoys
    -2.22
     साल
    -2.19
    ޞ
    -2.19
    訢
    -2.17
    POSITIVE LOGITS
    s
    3.08
    3
    2.95
    7
    2.92
    !”
    2.64
    .
    2.55
    1
    2.44
    time
    2.39
    4
    2.38
     renovación
    2.36
     Then
    2.31
    Activations Density 0.013%

    No Known Activations