© 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. 101631
    Prev
    Next
    INDEX
    Explanations

    stability and related concepts

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

    The neuron activates on words describing stability or instability (e.g. “stable,” “stability,” “wobble,” “wobbly,” “stabilization”).

    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
    嫑
    -1.73
     to
    -1.67
     continúa
    -1.48
    increases
    -1.40
     detaylı
    -1.40
    produces
    -1.39
    finds
    -1.36
     Calidad
    -1.35
     defying
    -1.35
     acredita
    -1.34
    POSITIVE LOGITS
     amikor
    1.59
    1.39
     “[
    1.36
    when
    1.36
    This
    1.36
    ”.
    1.35
    ஂ
    1.35
    !”
    1.33
    .”
    1.32
    U
    1.32
    Activations Density 0.018%

    No Known Activations