Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8091
    Prev
    Next
    INDEX
    Explanations

    words starting with ter

    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
     uniformes
    -0.87
     auroit
    -0.85
    striping
    -0.81
    navigationBar
    -0.81
    🆓
    -0.80
    jauh
    -0.79
    廊下
    -0.78
    Pants
    -0.77
     onStop
    -0.74
     escritora
    -0.74
    POSITIVE LOGITS
     Ter
    1.45
    Ter
    1.28
     ter
    1.13
     TER
    1.01
    Тер
    1.00
     Тер
    0.90
     termites
    0.88
     тер
    0.85
     termini
    0.85
     melancho
    0.84
    Activations Density 0.033%

    No Known Activations