© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 42124
    Prev
    Next
    INDEX
    Explanations

    dread, dreaded, dreadful, dredging

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

    The neuron strongly activates on the substring “dred”/“dread” appearing in words (e.g. dread, dreadful, dreaded, dreadlocks, dredge).

    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
     praktischen
    -2.89
     aktiven
    -2.84
     digitalen
    -2.81
    颳
    -2.80
     notwendigen
    -2.75
    薷
    -2.69
     erweiterten
    -2.66
    鉭
    -2.64
    瓩
    -2.63
    ⽬
    -2.61
    POSITIVE LOGITS
    ↵
    2.78
    a
    2.45
     bahwa
    2.39
    此外
    2.38
    :“
    2.36
    퐹
    2.36
    {
    2.30
    able
    2.28
    ,“
    2.17
    𝐒
    2.14
    Activations Density 0.002%

    No Known Activations