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. 8048
    Prev
    Next
    INDEX
    Explanations

    words starting with lam

    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
    車は
    -0.79
     quedado
    -0.75
    Rujuakan
    -0.75
    泵
    -0.72
     Oath
    -0.72
    指標
    -0.71
    なー
    -0.71
     increase
    -0.71
    França
    -0.70
     tracci
    -0.70
    POSITIVE LOGITS
     lam
    1.13
     LAM
    1.05
     Lam
    1.03
    LAM
    1.00
     lame
    1.00
     lamb
    0.97
    llar
    0.95
    lamo
    0.88
    Lam
    0.86
     Lamar
    0.85
    Activations Density 0.025%

    No Known Activations