© 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. 22-GEMMASCOPE-RES-131K
    7. 27718
    Prev
    Next
    INDEX
    Explanations

    currently or presently

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

    The neuron fires strongly on numeric values and measurements (e.g., years, counts, percentages).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     same
    -1.03
     both
    -1.02
    ッサ
    -0.87
    gamot
    -0.86
     deines
    -0.85
    了一眼
    -0.85
    onset
    -0.82
    ̳
    -0.81
    了出去
    -0.80
     sobald
    -0.79
    POSITIVE LOGITS
     currently
    3.63
     current
    3.27
     현재
    2.73
    Currently
    2.72
     actualmente
    2.69
    currently
    2.69
    当前
    2.64
     presently
    2.55
     сейчас
    2.55
    現在
    2.50
    Activations Density 0.135%

    No Known Activations