© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77826
    Prev
    Next
    INDEX
    Explanations

    Date and random generation

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

    The neuron is triggered by JavaScript date/time code, especially uses of the Date constructor or related getTime calls.

    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
     જે
    -0.74
    pst
    -0.73
     Titanic
    -0.72
    Filme
    -0.71
    ardless
    -0.71
    潛
    -0.71
     سرد
    -0.69
    matter
    -0.69
    oubted
    -0.66
     Bobo
    -0.65
    POSITIVE LOGITS
    szám
    0.76
    ről
    0.75
     siento
    0.75
    GrantedAuthority
    0.72
    онов
    0.71
    FIC
    0.70
    ongen
    0.70
    Double
    0.69
    textAppearance
    0.69
    restrial
    0.69
    Activations Density 0.024%

    No Known Activations