© 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. 107517
    Prev
    Next
    INDEX
    Explanations

    placeholder images or missing content

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

    The neuron detects occurrences of the word “placeholder.”

    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
     Popup
    -0.85
    Popup
    -0.84
     огне
    -0.82
    même
    -0.82
    tissa
    -0.81
    ทธิ
    -0.80
     Porcelain
    -0.77
     maroc
    -0.75
    _{+
    -0.73
     geg
    -0.73
    POSITIVE LOGITS
     placeholder
    1.81
    placeholder
    1.53
    Placeholder
    1.41
    Fallback
    1.38
     blank
    1.37
     default
    1.34
    fallback
    1.34
    getDefault
    1.33
    default
    1.32
     Placeholder
    1.30
    Activations Density 0.018%

    No Known Activations