© 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. 77590
    Prev
    Next
    INDEX
    Explanations

    each moment, day, or unit

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

    The neuron is tuned to quantifying words and phrases—especially tokens like “each,” “every,” “single,” and similar expressions of repetition or universality.

    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
     maje
    -1.00
     vives
    -0.98
     ordres
    -0.95
     ГО
    -0.94
     calendriers
    -0.92
     pantalon
    -0.92
     réalisateur
    -0.91
     visites
    -0.90
    mands
    -0.90
     arka
    -0.90
    POSITIVE LOGITS
     moment
    1.66
     minute
    1.65
     step
    1.17
     moments
    1.14
     opportunity
    1.11
     aspect
    1.11
     bit
    1.10
    Característica
    1.07
     every
    1.07
     tiny
    1.06
    Activations Density 0.035%

    No Known Activations