© 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. 70075
    Prev
    Next
    INDEX
    Explanations

    questions or code snippets

    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
     kilometer
    -0.93
    latter
    -0.84
    ettu
    -0.82
     Solubility
    -0.81
     Answered
    -0.81
     dandelion
    -0.79
     Hiram
    -0.79
    дное
    -0.79
    kwij
    -0.79
     CLOTH
    -0.78
    POSITIVE LOGITS
     javax
    1.16
     short
    1.14
    javax
    1.13
     Short
    1.12
    hort
    1.02
    short
    0.98
    Short
    0.98
    脚注の使い方
    0.75
    pinMode
    0.72
     Cheung
    0.71
    Activations Density 0.000%

    No Known Activations