© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62996
    Prev
    Next
    INDEX
    Explanations

    steps in a process

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

    The neuron detects words that signal procedural or methodological steps (e.g. “steps,” “required,” “procedures,” “used”).

    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
     extinción
    -1.13
    ੍ਰ
    -1.02
    expédition
    -1.01
    Selanjutnya
    -1.00
    Berdasarkan
    -0.99
    Sebelumnya
    -0.98
     silnik
    -0.97
    PINK
    -0.95
     飲み
    -0.95
     exportación
    -0.95
    POSITIVE LOGITS
     steps
    1.59
     towards
    1.57
     toward
    1.50
     in
    1.41
     to
    1.39
     taken
    1.37
     process
    1.30
     involved
    1.26
     menuju
    1.20
    ในการ
    1.16
    Activations Density 0.026%

    No Known Activations