© 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. 22-GEMMASCOPE-RES-131K
    7. 33110
    Prev
    Next
    INDEX
    Explanations

    collection and list structures

    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
    ↵↵
    -1.00
    iega
    -1.00
    bama
    -0.90
    тинка
    -0.89
    moja
    -0.88
    information
    -0.87
    графі
    -0.85
    BRD
    -0.85
    ginfo
    -0.85
    colm
    -0.84
    POSITIVE LOGITS
     які
    1.05
     []*
    1.04
    𝓋
    0.94
    饜
    0.94
    注意事
    0.93
     spus
    0.91
     pensa
    0.90
    voyer
    0.90
     đựng
    0.89
     geleverd
    0.89
    Activations Density 0.034%

    No Known Activations