© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 8933
    Prev
    Next
    INDEX
    Explanations

    electronic components and devices

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

    This neuron detects mentions of Bluetooth‐based “Beacon” technologies (e.g. Eddystone/iBeacon and related beacon tokens).

    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
     of
    -1.53
    Though
    -1.34
    Despite
    -1.31
    Unlike
    -1.30
    Even
    -1.28
     valla
    -1.23
    Not
    -1.22
    話は
    -1.22
    》:
    -1.21
     podkre
    -1.20
    POSITIVE LOGITS
    pentru
    1.41
     이름
    1.31
    chea
    1.23
    gebäude
    1.23
    beruf
    1.18
     either
    1.18
     srdce
    1.18
     bytu
    1.17
     ส์
    1.16
     called
    1.16
    Activations Density 0.078%

    No Known Activations