© 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. 40959
    Prev
    Next
    INDEX
    Explanations

    disc player, disc drive, disc diffusion

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

    The neuron fires whenever the text contains the substring “disc” (including its plural or compound forms).

    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
     they
    -2.66
    却又
    -2.55
    “
    -2.53
    却不
    -2.38
     itinéraire
    -2.30
    進去
    -2.20
    籀
    -2.19
    鹇
    -2.16
    也沒
    -2.16
     撮っ
    -2.16
    POSITIVE LOGITS
    '
    2.36
    可以
    2.25
    März
    2.22
    锖
    2.22
    2.22
    处理
    2.16
    ﻒ
    2.14
    ).
    2.11
    "
    2.09
    是啊
    2.02
    Activations Density 0.020%

    No Known Activations