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. 60
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
    真実
    -0.94
    lenie
    -0.91
    viated
    -0.90
     Exped
    -0.89
    lidad
    -0.88
    wakili
    -0.88
    reated
    -0.85
     imaginar
    -0.84
     хвати
    -0.84
    rophilic
    -0.83
    POSITIVE LOGITS
    arture
    0.95
    了不少
    0.86
    캘
    0.85
    daan
    0.80
    ifornia
    0.80
     penampilan
    0.77
    entification
    0.77
    铝
    0.77
     commer
    0.76
    出品
    0.75
    Activations Density 0.005%

    No Known Activations