© 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. 59126
    Prev
    Next
    INDEX
    Explanations

    dates and times

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

    The neuron strongly activates on numeric temporal markers—especially years and timestamps.

    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
    😟
    -0.88
     pany
    -0.85
    atha
    -0.85
    tine
    -0.85
    🤡
    -0.85
    😐
    -0.84
    Tam
    -0.84
    hawk
    -0.83
     FileNotFound
    -0.82
     🥲
    -0.81
    POSITIVE LOGITS
    </blockquote>
    1.31
    ");
    0.98
     ");
    0.91
    ">
    0.84
     Schrifts
    0.83
     attracted
    0.81
     приго
    0.81
     );
    0.80
     });
    0.79
     intrigued
    0.79
    Activations Density 0.001%

    No Known Activations