© 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. 93504
    Prev
    Next
    INDEX
    Explanations

    periodicity of publications

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

    The neuron flags terms that specify publication or event frequency (e.g. monthly, quarterly, annual, triannual).

    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
     week
    -1.14
    Week
    -0.98
     Week
    -0.92
    WEEK
    -0.92
     WEEK
    -0.90
     daily
    -0.90
    week
    -0.88
     Weekly
    -0.86
    Daily
    -0.85
     Woche
    -0.85
    POSITIVE LOGITS
     quarterly
    4.66
     Quarterly
    3.48
    Quarterly
    3.13
     bian
    2.92
    quar
    2.58
     QUARTER
    2.48
     quarter
    2.39
    季度
    2.08
     quarters
    1.88
     bi
    1.88
    Activations Density 0.081%

    No Known Activations