© 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. 27546
    Prev
    Next
    INDEX
    Explanations

    now, time, after

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

    The neuron responds to unusually long spans of continuous text—i.e. long sentences or multi-clause passages.

    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
    altra
    -1.08
     dezelve
    -1.03
    mogen
    -0.96
    licopter
    -0.95
    ulur
    -0.95
     honn
    -0.94
     geene
    -0.93
     vloer
    -0.91
     kazak
    -0.90
     могат
    -0.89
    POSITIVE LOGITS
     сейчас
    1.20
     jetzt
    0.95
     but
    0.94
     now
    0.93
     during
    0.93
     после
    0.91
     mengikuti
    0.91
    userdetails
    0.90
     sonrası
    0.88
     last
    0.86
    Activations Density 0.017%

    No Known Activations