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. 8312
    Prev
    Next
    INDEX
    Explanations

    popular among

    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
     or
    -1.36
     while
    -1.00
     without
    -0.96
     без
    -0.94
     which
    -0.91
     that
    -0.87
    guitarra
    -0.85
     manchmal
    -0.84
     вместо
    -0.82
    ventricular
    -0.82
    POSITIVE LOGITS
     auprès
    2.45
     among
    2.23
     среди
    1.97
     amongst
    1.88
     wśród
    1.87
    among
    1.84
     parmi
    1.55
     blant
    1.53
     серед
    1.45
     لدى
    1.44
    Activations Density 0.095%

    No Known Activations