© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 8183
    Prev
    Next
    INDEX
    Explanations

    worry about

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

    Neuron 4 is keyed to the phrase “worry about,” activating strongly on occurrences of that construction.

    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
    enseur
    -1.46
    を使い
    -1.45
     pulsa
    -1.41
    鲧
    -1.41
     contactez
    -1.39
     bekämp
    -1.34
    
    -1.34
    );
    -1.34
    Ꮂ
    -1.34
     découvrez
    -1.32
    POSITIVE LOGITS
     of
    2.17
     and
    1.41
     \&
    1.37
    \
    1.34
    ably
    1.34
     is
    1.33
    方法は
    1.32
     која
    1.29
    lında
    1.29
    aute
    1.27
    Activations Density 0.004%

    No Known Activations