© 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. 635
    Prev
    Next
    INDEX
    Explanations

    second and second-guessing

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

    The main thing this neuron does is detect numeric expressions and units of measurement (e.g. digits and measurement terms).

    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
    Voci
    -0.86
    Uma
    -0.76
     responsabili
    -0.75
    моро
    -0.73
    митри
    -0.73
     Immune
    -0.71
     Wettbewer
    -0.71
    anément
    -0.71
    urlaub
    -0.71
     Houd
    -0.70
    POSITIVE LOGITS
     seconded
    3.89
     second
    3.63
    second
    3.20
    Second
    3.00
    secon
    2.92
     Second
    2.75
     seconds
    2.75
    SECOND
    2.52
     SECOND
    2.39
     seconde
    2.16
    Activations Density 0.009%

    No Known Activations