© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 70170
    Prev
    Next
    INDEX
    Explanations

    programming and code elements

    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
    を失
    -0.81
     renkli
    -0.70
    gura
    -0.69
    észet
    -0.68
     Từ
    -0.68
     MonoBehaviour
    -0.68
    Morte
    -0.66
    paragraphs
    -0.66
    WTO
    -0.66
     universe
    -0.65
    POSITIVE LOGITS
    タ
    0.72
     unbelief
    0.69
     collectible
    0.68
    カツ
    0.67
    diman
    0.67
    超人
    0.66
    SECTION
    0.65
    ikke
    0.65
     izd
    0.65
    ayaan
    0.64
    Activations Density 0.057%

    No Known Activations