© 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. 64443
    Prev
    Next
    INDEX
    Explanations

    grant proposals

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

    The neuron detects numeric tokens—sequences of digits (e.g. years, measurement values, catalogue numbers) in scientific or technical 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
    udesta
    -0.85
     puntual
    -0.79
     enumerated
    -0.77
     peta
    -0.75
     Occidente
    -0.74
    PCI
    -0.73
    彼得
    -0.72
     APM
    -0.72
     Phal
    -0.72
    salida
    -0.72
    POSITIVE LOGITS
     proposal
    1.42
     Proposal
    1.22
     proposals
    1.16
    Proposal
    1.06
    proposal
    1.05
     allocation
    1.05
     telescope
    1.04
     scientific
    1.02
     proposing
    1.00
     proposer
    0.98
    Activations Density 0.019%

    No Known Activations