© 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. 41368
    Prev
    Next
    INDEX
    Explanations

    blasio, blaszyk, blasband, echobox

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

    The neuron fires on occurrences of the character sequence “blas” (as in names like de Blasio or Blaszyk).

    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
    荟
    -2.81
    鏖
    -2.69
    érables
    -2.50
    鲻
    -2.48
     apetito
    -2.47
    t
    -2.44
    蕓
    -2.38
    
    -2.38
     querido
    -2.34
    ﮧ
    -2.34
    POSITIVE LOGITS
    “
    3.75
    2
    3.17
    1
    2.94
    i
    2.41
    5
    2.39
    '
    2.30
    ientras
    2.27
    ぷ
    2.22
    6
    2.14
     nimmer
    2.13
    Activations Density 0.004%

    No Known Activations