© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 74373
    Prev
    Next
    INDEX
    Explanations

    dating from history or for services

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

    The neuron detects occurrences of the word “dating.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    IANGLES
    -2.47
    DebuggerStep
    -2.34
    chtenstein
    -2.33
    ativis
    -2.33
     sonidos
    -2.31
    ጁ
    -2.27
    』(
    -2.27
    がございます
    -2.25
    tigung
    -2.23
    řeba
    -2.23
    POSITIVE LOGITS
    C
    3.08
     foremost
    2.94
    -
    2.80
    O
    2.67
    But
    2.47
    of
    2.47
    ..,
    2.47
    that
    2.45
    A
    2.42
     tomando
    2.41
    Activations Density 0.006%

    No Known Activations