© 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. 48300
    Prev
    Next
    INDEX
    Explanations

    accretion disks

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

    The main thing this neuron does is detect dense scientific‐technical terminology (especially astrophysics and related physical‐science 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
     onPostExecute
    -0.81
    linalg
    -0.78
     peptides
    -0.76
    namt
    -0.76
    首歌
    -0.75
     sociologists
    -0.73
     Jenkins
    -0.73
     peptide
    -0.72
    Jenkins
    -0.72
     kilometres
    -0.72
    POSITIVE LOGITS
     accretion
    1.59
     disk
    1.34
     Disk
    1.24
    DISK
    1.21
    disk
    1.20
    Disk
    1.16
     disc
    1.12
     disks
    1.00
    disc
    0.97
    disks
    0.91
    Activations Density 0.032%

    No Known Activations