© 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. 22-GEMMASCOPE-RES-131K
    7. 70884
    Prev
    Next
    INDEX
    Explanations

    rooted devices

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

    The neuron detects technical Android‐modding jargon—terms related to rooted devices and custom ROM modifications.

    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
     our
    -1.90
     мы
    -1.48
    ₄
    -1.46
     we
    -1.46
    ₆
    -1.38
     tumbuhan
    -1.38
     fuß
    -1.34
     правительства
    -1.34
     ciclismo
    -1.33
     угло
    -1.33
    POSITIVE LOGITS
    眼泪
    1.61
    endaftar
    1.45
    𝐱
    1.34
     电影
    1.30
     Tourisme
    1.28
    素晴
    1.27
    𓈒
    1.27
    🪛
    1.27
     Dernière
    1.26
    onsumsi
    1.26
    Activations Density 0.056%

    No Known Activations