© 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. 34-GEMMASCOPE-RES-131K
    7. 77135
    Prev
    Next
    INDEX
    Explanations

    Broadcast Receiver

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

    The neuron flags specialized technical‐jargon tokens (e.g. simulation “fix”/“gravity” keywords or programming API class names like “BroadcastReceiver”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     spark
    -0.68
     AllMovie
    -0.66
     antwortete
    -0.62
    ulx
    -0.61
    ビー
    -0.60
     ^^^
    -0.60
     Dependent
    -0.59
     Mier
    -0.59
     hom
    -0.59
     scut
    -0.58
    POSITIVE LOGITS
    Collect
    0.77
    жат
    0.74
    ">{
    0.73
     सि
    0.73
    收藏
    0.72
    Ⱦ
    0.70
     fores
    0.68
     glacial
    0.67
    ALING
    0.66
    erals
    0.66
    Activations Density 0.063%

    No Known Activations