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. 8568
    Prev
    Next
    INDEX
    Explanations

    Felix

    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
     Seamless
    -0.91
     naše
    -0.82
     Maske
    -0.78
     jedno
    -0.77
     chcą
    -0.76
     Collapse
    -0.74
    が無
    -0.73
     kemajuan
    -0.73
     dichos
    -0.73
     likely
    -0.73
    POSITIVE LOGITS
     Felix
    1.08
    Felix
    1.07
    Felic
    0.91
    Fé
    0.86
     Felic
    0.82
     felix
    0.81
     Auger
    0.80
     felic
    0.79
     Felicia
    0.78
    थि
    0.74
    Activations Density 0.009%

    No Known Activations