© 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. 75860
    Prev
    Next
    INDEX
    Explanations

    periods and phases

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

    The neuron strongly activates on domain-specific topic nouns—words that name the main subject or focus of a section or study (e.g. pregnancy, festival, campaign, outbreak, chemotherapy, septic shock, etc.).

    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
     durante
    -1.73
     during
    -1.56
    during
    -1.31
     tijdens
    -1.24
     podczas
    -1.20
     počas
    -1.16
     während
    -1.16
     DURING
    -1.13
    Durante
    -1.11
     během
    -1.06
    POSITIVE LOGITS
     period
    2.11
     periods
    1.45
     berlangsung
    1.43
     time
    1.34
    period
    1.27
     periode
    1.17
     phase
    1.16
     وبعد
    1.10
    periode
    1.10
    Period
    1.09
    Activations Density 0.147%

    No Known Activations