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. 8146
    Prev
    Next
    INDEX
    Explanations

    numbers and mathematical operations

    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
     Gait
    -0.73
     considérons
    -0.71
    textnormal
    -0.71
     unsuccessful
    -0.69
    annulation
    -0.66
    text
    -0.66
     Opfer
    -0.66
    ğa
    -0.65
     jaunes
    -0.65
     within
    -0.64
    POSITIVE LOGITS
     festgestellt
    0.76
    dotti
    0.75
    在这里
    0.74
     äldre
    0.73
    reinigung
    0.73
    iov
    0.73
     Spicer
    0.72
    ússia
    0.72
     thee
    0.71
    érience
    0.71
    Activations Density 0.036%

    No Known Activations