© 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. 39691
    Prev
    Next
    INDEX
    Explanations

    asset tracking systems

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

    The neuron spikes on domain-specific jargon and acronyms (e.g. “NB-IoT,” “LoRa,” “asset tracking,” “machine-type,” “applicationId”), i.e. technical or specialized proper names and initialisms.

    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
     paesaggio
    -1.52
     villaggio
    -1.52
     онъ
    -1.52
     gani
    -1.52
    ouſ
    -1.51
    bluza
    -1.48
    Wii
    -1.48
    䊉
    -1.43
     iſt
    -1.41
    goodsimage
    -1.41
    POSITIVE LOGITS
    ).
    1.44
    A
    1.35
    ",
    1.34
    ...
    1.23
    ,
    1.21
     []
    1.20
     TO
    1.20
     Vi
    1.19
    e
    1.19
    s
    1.16
    Activations Density 0.022%

    No Known Activations