© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98516
    Prev
    Next
    INDEX
    Explanations

    \mathrm{d}

    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
     навчання
    -0.93
    兒子
    -0.85
     membantu
    -0.85
     壓
    -0.82
     هنا
    -0.80
     σω
    -0.80
    怖い
    -0.78
     налого
    -0.78
    atchewan
    -0.78
     tchèque
    -0.78
    POSITIVE LOGITS
    多吃
    0.81
     gastronomía
    0.80
     Beats
    0.79
     yng
    0.79
    Jau
    0.79
    Signed
    0.79
    EXHIBIT
    0.78
     nullable
    0.78
     पढ़
    0.77
     famili
    0.76
    Activations Density 0.005%

    No Known Activations