© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12903
    Prev
    Next
    INDEX
    Explanations

    also too afterwards

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

    The neuron fires on content‐bearing noun tokens (object names, technical terms, etc.).

    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
     and
    -1.15
     your
    -0.96
     our
    -0.94
    oooooo
    -0.90
    norme
    -0.90
     not
    -0.88
    īgā
    -0.87
     both
    -0.86
    ooooooo
    -0.86
     ngayon
    -0.85
    POSITIVE LOGITS
     afterwards
    1.45
     też
    1.20
     afterward
    1.15
     نیز
    1.08
     también
    1.05
     тоже
    1.04
     too
    1.02
     if
    1.02
     също
    0.98
     tiež
    0.97
    Activations Density 0.063%

    No Known Activations