© 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. 10-GEMMASCOPE-RES-131K
    7. 1728
    Prev
    Next
    INDEX
    Explanations

    challenge and subsequent words

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

    The neuron detects occurrences of the word “challenge” (including its inflected forms: challenged, challenges, challenging).

    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
    a
    -2.17
    .
    -2.08
     was
    -1.73
    <strong>
    -1.69
     be
    -1.66
    i
    -1.61
     a
    -1.60
    {
    -1.60
    as
    -1.53
    UL
    -1.51
    POSITIVE LOGITS
    itiert
    1.84
     Şubat
    1.73
    ⃢
    1.71
    ₂,
    1.70
     נגד
    1.70
    ޏ
    1.69
    妧
    1.68
    /}.
    1.66
     sommige
    1.66
    vimento
    1.66
    Activations Density 0.014%

    No Known Activations