© 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. 32826
    Prev
    Next
    INDEX
    Explanations

    diamond shelf size

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

    The neuron is triggered by standalone identifiers or field‐label tokens (e.g. code/configuration names like “License,” “Name,” “Size,” “dart,” “given,” etc.).

    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
     defStyle
    -0.81
    ذر
    -0.80
    Background
    -0.79
    싣
    -0.76
     handwriting
    -0.75
    tighets
    -0.71
     hundreds
    -0.71
    𝔡
    -0.71
     Revival
    -0.69
    bg
    -0.69
    POSITIVE LOGITS
     size
    1.30
     semantic
    1.08
     Size
    1.08
     color
    1.05
    size
    1.02
    semantic
    0.95
     sizes
    0.92
     Размер
    0.90
     Größe
    0.90
     رنگ
    0.89
    Activations Density 0.001%

    No Known Activations