Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8617
    Prev
    Next
    INDEX
    Explanations

    Heerbrandt, Steen Solution

    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
     Dép
    -0.98
     الاسلام
    -0.88
    𝓌
    -0.81
    军团
    -0.80
     Dacă
    -0.79
    uttering
    -0.79
     opérateur
    -0.79
     Mémoire
    -0.78
    펭
    -0.77
     citar
    -0.77
    POSITIVE LOGITS
     besonder
    0.85
    ў
    0.84
    le
    0.80
    mundo
    0.80
    َه
    0.78
    abyrinth
    0.77
     đời
    0.77
    ^{-}\
    0.77
    am
    0.76
    Acknowledgments
    0.76
    Activations Density 0.040%

    No Known Activations