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. 7980
    Prev
    Next
    INDEX
    Explanations

    words starting with tiny

    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
    所以在
    -0.91
    stateMutability
    -0.84
    Immun
    -0.80
     プレミアム
    -0.76
    chb
    -0.76
    ch
    -0.75
     et
    -0.73
     larg
    -0.73
     goodies
    -0.73
    technologies
    -0.72
    POSITIVE LOGITS
     tiny
    2.03
    tiny
    1.88
     Tiny
    1.80
    Tiny
    1.76
     малень
    1.34
     little
    1.24
    🤏
    1.23
     tots
    1.18
    URL
    1.13
     insignificant
    1.13
    Activations Density 0.011%

    No Known Activations