© 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. 76140
    Prev
    Next
    INDEX
    Explanations

    saddle points eigenvalues equilibrium

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

    This neuron activates on technical terms describing dynamical‐systems behavior—especially chaos—such as “unstable,” “periodic,” “orbits,” and related phase/plot vocabulary.

    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
    NSON
    -0.79
    GARD
    -0.76
    données
    -0.76
     منظ
    -0.74
     汉
    -0.72
    mlb
    -0.72
    strukturen
    -0.71
    ghan
    -0.71
    ViewGroup
    -0.71
     heap
    -0.71
    POSITIVE LOGITS
     equilibrium
    1.09
     saddles
    0.91
     stability
    0.91
     there
    0.82
     equilibria
    0.81
     Equilibrium
    0.80
    平衡
    0.79
     estabilidad
    0.78
     eigenvalues
    0.77
     saddle
    0.77
    Activations Density 0.023%

    No Known Activations