© 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. 98704
    Prev
    Next
    INDEX
    Explanations

    numbers and specific punctuation

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

    The neuron detects numeric time codes (timestamps) typically found in subtitle/caption blocks.

    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
     in
    -1.05
    ⟨
    -0.99
     of
    -0.97
     elever
    -0.96
     according
    -0.96
     dansk
    -0.94
    が
    -0.94
    gupta
    -0.93
    も
    -0.91
    ventus
    -0.91
    POSITIVE LOGITS
     nachher
    1.03
     رسد
    0.93
     Makes
    0.92
     then
    0.91
     determinadas
    0.91
     vermutlich
    0.90
     freilich
    0.90
     descubierto
    0.87
     Gehalt
    0.86
     Herkunft
    0.85
    Activations Density 0.000%

    No Known Activations