© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74052
    Prev
    Next
    INDEX
    Explanations

    words starting with Kre

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

    The neuron strongly activates on the substring “kre” (e.g. in tokens like “Kreis,” “Kremlin,” “Krebs”).

    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
    ↵↵
    -4.25
    \
    -3.64
    {
    -3.06
     unveils
    -2.80
     a
    -2.77
    <
    -2.70
    ?
    -2.59
     reiter
    -2.45
     основных
    -2.44
    ,,
    -2.42
    POSITIVE LOGITS
     間取り
    3.14
    
    3.13
    鲣
    3.08
    鵟
    2.91
     groundbreaking
    2.88
    酲
    2.72
    璆
    2.59
    untuk
    2.56
     artful
    2.53
    嫗
    2.52
    Activations Density 0.002%

    No Known Activations