© 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. 34-GEMMASCOPE-RES-131K
    7. 78267
    Prev
    Next
    INDEX
    Explanations

    scientific/technical phrases

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

    This neuron detects mentions of astronomical instruments or facilities (e.g., telescope and observatory names and their acronyms).

    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
    paddingRight
    -0.79
     Maulana
    -0.75
    Примечания
    -0.74
    牧
    -0.74
    acyj
    -0.73
    ぴ
    -0.72
     peně
    -0.72
    イヤル
    -0.72
    株式
    -0.69
     AIAA
    -0.69
    POSITIVE LOGITS
     queue
    0.91
    colla
    0.84
     dich
    0.80
     cameras
    0.80
    вез
    0.79
     Canada
    0.79
     camera
    0.78
    tomat
    0.76
     extremes
    0.76
     Adaptive
    0.75
    Activations Density 0.026%

    No Known Activations