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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117386
    Prev
    Next
    INDEX
    Explanations

    multi-language technical text

    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
    erst
    -0.83
    partial
    -0.79
    🤷
    -0.79
    urther
    -0.77
    👍🏻
    -0.75
     hah
    -0.75
     IndexError
    -0.74
    😆
    -0.73
     MASK
    -0.73
     hee
    -0.73
    POSITIVE LOGITS
    enterian
    0.95
    clientX
    0.84
    asilkan
    0.81
    学习
    0.81
    дешь
    0.72
    omials
    0.71
    ليد
    0.70
    edal
    0.70
    パッケージ
    0.69
    特集
    0.69
    Activations Density 0.003%

    No Known Activations