© 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. 65248
    Prev
    Next
    INDEX
    Explanations

    holding cats or ears

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

    The main thing this neuron does is detect words denoting actions or motion (i.e. verbs describing doing, moving, or performing).

    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
    ↵
    -1.80
     bocetos
    -1.35
    のだが
    -1.34
     pertama
    -1.32
     válida
    -1.26
     prawidł
    -1.24
     should
    -1.23
     about
    -1.20
     agregó
    -1.20
     диза
    -1.18
    POSITIVE LOGITS
     {
    1.35
     the
    1.33
    czeniu
    1.26
    덫
    1.23
     dégustation
    1.23
     سبيل
    1.22
    Gesam
    1.22
     blancas
    1.21
    ]}$
    1.20
    zzlement
    1.20
    Activations Density 0.005%

    No Known Activations