© 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. 34-GEMMASCOPE-RES-131K
    7. 76757
    Prev
    Next
    INDEX
    Explanations

    state-space models

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

    This neuron detects technical control‐theory and state-estimation jargon (e.g. “Kalman,” “filter,” “recursive,” “system,” “nonlinear,” “state‐space,” “derivative”).

    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
     octombrie
    -0.77
    URRED
    -0.76
    Pascal
    -0.76
    yama
    -0.74
    softmax
    -0.73
     kezel
    -0.71
    וצ
    -0.71
     hivat
    -0.71
    larının
    -0.70
     otomatig
    -0.70
    POSITIVE LOGITS
     state
    1.80
     states
    1.48
     dynamics
    1.43
    State
    1.41
    state
    1.36
     State
    1.35
    STATE
    1.34
    システム
    1.30
     STATE
    1.24
    状态
    1.23
    Activations Density 0.038%

    No Known Activations