© 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. 22-GEMMASCOPE-RES-131K
    7. 67818
    Prev
    Next
    INDEX
    Explanations

    on weekend

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

    The neuron activates on the blank‐line or paragraph‐break separators that mark boundaries between distinct news items.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     then
    -1.70
     there
    -1.53
     so
    -1.53
     when
    -1.52
     to
    -1.51
     you
    -1.38
     can
    -1.38
     each
    -1.38
     I
    -1.34
     because
    -1.34
    POSITIVE LOGITS
     according
    1.32
    ほとん
    1.31
     consommateurs
    1.27
    ύ
    1.25
    according
    1.23
    あー
    1.23
    凄く
    1.20
     apetito
    1.19
     DÍA
    1.19
     repuesto
    1.19
    Activations Density 0.156%

    No Known Activations