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. 87
    Prev
    Next
    INDEX
    Explanations

    linking words or phrases

    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
     foncé
    -0.91
    ṛ
    -0.91
    𓐍
    -0.86
     herbes
    -0.85
     jackpot
    -0.85
     technolog
    -0.85
    .-
    -0.85
    Serves
    -0.84
     بیت
    -0.84
    Какво
    -0.84
    POSITIVE LOGITS
     its
    0.94
     primarily
    0.92
     money
    0.91
    ograp
    0.90
     mostly
    0.88
     mainly
    0.84
    เมือง
    0.79
    rceil
    0.79
     terutama
    0.78
    έρα
    0.77
    Activations Density 0.155%

    No Known Activations