© 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. 77714
    Prev
    Next
    INDEX
    Explanations

    ICP-MS, Orbitrap, MonoVista

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

    scientific instruments and measurement techniques like mass spectrometers, spectroscopy equipment, and microscopes.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on specialized scientific instrumentation and analysis terms—names of measurement techniques, instruments, and their technical 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
     cam
    -0.80
     صوتيه
    -0.77
     Jedes
    -0.73
     வரு
    -0.73
    자가
    -0.72
     bringe
    -0.71
     Elektronik
    -0.71
     llegando
    -0.71
     géographie
    -0.70
     firebaseConfig
    -0.70
    POSITIVE LOGITS
     gorą
    0.77
     sistemas
    0.76
     movimientos
    0.75
    Connections
    0.74
     Impacts
    0.74
    nosti
    0.74
    oudou
    0.73
    Domain
    0.73
     کره
    0.71
     graphi
    0.70
    Activations Density 0.033%

    No Known Activations