© 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. 89834
    Prev
    Next
    INDEX
    Explanations

    blended ingredients

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

    The main thing this neuron does is pick out imperative or step‐action verbs in procedural or instructional text (e.g. cooking and process steps).

    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
     rengi
    -0.92
    gger
    -0.90
    baus
    -0.90
    юрпри
    -0.87
    linde
    -0.87
     yeri
    -0.86
     samochodu
    -0.85
     الصحية
    -0.85
    ConstraintLayout
    -0.84
     الموا
    -0.83
    POSITIVE LOGITS
     mixture
    3.39
     mixtures
    2.08
    mixture
    1.98
     Mixture
    1.92
    Mixture
    1.77
     mix
    1.63
     смесь
    1.54
    混合
    1.52
     solution
    1.46
     Mixtures
    1.45
    Activations Density 0.030%

    No Known Activations