© 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. 34593
    Prev
    Next
    INDEX
    Explanations

    the name of things

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    姓
    -0.90
     phrases
    -0.89
     Saying
    -0.85
    WORD
    -0.82
     слово
    -0.82
     nicknamed
    -0.82
     phrase
    -0.81
    word
    -0.80
    のことを
    -0.79
    uppertal
    -0.79
    POSITIVE LOGITS
     name
    2.38
    name
    1.28
     names
    1.15
     navn
    1.06
    名称
    1.06
     Name
    0.98
    名
    0.91
     nombre
    0.86
     náz
    0.85
    ":[{
    0.84
    Activations Density 0.092%

    No Known Activations