© 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. 34-GEMMASCOPE-RES-131K
    7. 90274
    Prev
    Next
    INDEX
    Explanations

    past events or individuals

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

    The neuron is selectively activating on writing that appears to be a user’s technical question text—i.e. tokens inside the "Q:" question bodies.

    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
    èces
    -0.96
    бую
    -0.94
    waran
    -0.91
    Anno
    -0.91
     noise
    -0.90
    쏘
    -0.89
    ੭
    -0.89
    되는
    -0.88
    凋
    -0.88
    𝙁
    -0.88
    POSITIVE LOGITS
     previous
    2.19
     someone
    1.94
     somebody
    1.85
     recent
    1.73
     whoever
    1.70
    previous
    1.63
    Whoever
    1.53
     предыду
    1.50
     recently
    1.50
    someone
    1.45
    Activations Density 0.077%

    No Known Activations