© 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. 32132
    Prev
    Next
    INDEX
    Explanations

    injecting fluids or substances

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

    technical descriptions of physical components and structures in scientific or engineering contexts.

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

    The neuron activates on numerical tokens (figures, measurements, and numeric data) in scientific text.

    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
     Velocity
    -0.97
     Seminary
    -0.88
     Wak
    -0.85
     radikal
    -0.85
     jao
    -0.83
    dotte
    -0.82
     trener
    -0.82
     plastik
    -0.81
    seigneur
    -0.81
     divination
    -0.81
    POSITIVE LOGITS
     injection
    0.92
     inject
    0.84
     Injection
    0.77
     angeb
    0.77
    injection
    0.75
    bless
    0.74
    meable
    0.73
     injecting
    0.73
    Injection
    0.71
     Inject
    0.70
    Activations Density 0.034%

    No Known Activations