© 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. 50408
    Prev
    Next
    INDEX
    Explanations

    words starting with 'Ch'

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

    The neuron is highly activated by tokens containing the bigram “Ch,” effectively detecting any token that begins with “Ch.”

    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
     Ganze
    -0.88
     disparition
    -0.85
    ดิ
    -0.84
     now
    -0.82
     how
    -0.81
    ed
    -0.81
    みて
    -0.80
    しても
    -0.79
    none
    -0.79
    as
    -0.77
    POSITIVE LOGITS
     Ch
    1.68
     ch
    1.55
    Ch
    1.50
     CH
    1.22
     Chré
    1.02
     CHF
    1.01
    胆
    0.97
    mės
    0.92
    wirkung
    0.91
     Chuk
    0.90
    Activations Density 0.030%

    No Known Activations