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. 8005
    Prev
    Next
    INDEX
    Explanations

    the following

    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
     conster
    -1.13
    razine
    -1.06
    очень
    -1.02
     Objetivos
    -1.02
    rizona
    -1.02
    🔝
    -1.02
    БК
    -1.02
    vantages
    -1.02
    mentes
    -1.01
     getNombre
    -1.01
    POSITIVE LOGITS
     last
    1.78
     following
    1.74
     only
    1.71
     first
    1.65
     second
    1.50
     latter
    1.46
     previous
    1.45
     same
    1.43
     other
    1.39
     there
    1.38
    Activations Density 0.044%

    No Known Activations