© 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. 129995
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on words that signal a full or finalized release or launch—terms like “real,” “full,” “permanent,” and “launch.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    full launch or completion

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ܧ
    -1.16
     Gebiete
    -1.02
    successfully
    -1.01
     Veränderung
    -0.99
    perfectly
    -0.98
     attraverso
    -0.98
     hled
    -0.96
    ajaan
    -0.95
    ܞ
    -0.94
    謦
    -0.93
    POSITIVE LOGITS
     after
    1.05
    正式
    0.99
     полноцен
    0.97
     From
    0.94
     вд
    0.94
    kete
    0.91
    rı
    0.89
     instead
    0.89
     оконча
    0.88
    ssymb
    0.88
    Activations Density 0.041%

    No Known Activations