© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58855
    Prev
    Next
    INDEX
    Explanations

    loss of electricity or service

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

    The neuron detects mentions of electricity or power outages (loss of power or “no power” situations).

    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
     土産
    -1.35
    ovico
    -1.34
    同じ
    -1.29
     that
    -1.24
     setUsername
    -1.23
     secondi
    -1.23
     smör
    -1.23
     autunno
    -1.20
    ündigung
    -1.20
     OPINION
    -1.20
    POSITIVE LOGITS
     zunächst
    1.17
    <0xE6>
    1.14
    aniem
    1.13
     terminar
    1.13
     зачем
    1.13
     Really
    1.13
    все
    1.11
    示意图
    1.11
    рила
    1.11
     excell
    1.10
    Activations Density 0.036%

    No Known Activations