© 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. 34-GEMMASCOPE-RES-131K
    7. 1125
    Prev
    Next
    INDEX
    Explanations

    names starting with h

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

    The neuron fires on numeric tokens representing years (e.g., four‐digit dates in birth/death parentheses).

    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
    accine
    -0.98
     acudi
    -0.96
     meinem
    -0.96
    omyces
    -0.94
     Drittel
    -0.89
     merkwür
    -0.88
     Verkäufer
    -0.87
    TProtocol
    -0.87
     aislado
    -0.85
     sababu
    -0.84
    POSITIVE LOGITS
     hry
    1.63
     হ
    1.59
    ห
    1.48
     ħ
    1.42
     hro
    1.41
     հ
    1.37
     ಹ
    1.36
     હ
    1.34
     ہ
    1.29
     hydrochloride
    1.29
    Activations Density 0.542%

    No Known Activations