© 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. 22-GEMMASCOPE-RES-131K
    4. 104405
    Prev
    Next
    INDEX
    Explanations

    key highlights and takeaways

    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_22/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
     a
    -1.09
     your
    -1.06
    lamak
    -1.05
     когда
    -1.02
     aktif
    -0.96
    reiben
    -0.94
    ទ
    -0.92
     atlet
    -0.91
    getMenuInflater
    -0.91
    を描
    -0.90
    POSITIVE LOGITS
    particular
    1.20
     particular
    1.18
    particularly
    1.12
    Notable
    1.10
     particolare
    1.09
     åren
    1.05
    Particular
    1.05
     особенно
    1.03
     özellikle
    1.03
     partic
    0.99
    Activations Density 0.050%

    No Known Activations