© 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. 70700
    Prev
    Next
    INDEX
    Explanations

    amorphous glass

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

    The neuron activates strongly on terms referring to non-crystalline solids (e.g. glass, vitreous, amorphous, disordered)

    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
    
    -1.42
    穑
    -1.33
     erns
    -1.27
    婊
    -1.27
     sings
    -1.27
    ecycle
    -1.27
     gasolina
    -1.27
     обслужи
    -1.27
     meat
    -1.24
     ajuda
    -1.24
    POSITIVE LOGITS
    0
    1.52
    {
    1.45
    。
    1.30
    ，“
    1.22
    “
    1.21
    udayaan
    1.20
    。“
    1.19
     Rodríguez
    1.16
    équation
    1.13
     Before
    1.13
    Activations Density 0.061%

    No Known Activations