© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35506
    Prev
    Next
    INDEX
    Explanations

    Zaïre, Bandstand, Regulation

    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
     perla
    -1.00
     reafon
    -0.94
     huid
    -0.91
    包
    -0.89
    篮球
    -0.85
     preved
    -0.85
     atacante
    -0.85
    涝
    -0.83
     complètes
    -0.83
    ệu
    -0.83
    POSITIVE LOGITS
     parlak
    1.04
     desmotiv
    0.98
     health
    0.94
    Française
    0.94
     such
    0.92
     tuturor
    0.92
     Versicher
    0.90
     “.
    0.89
     წ
    0.88
    throughout
    0.88
    Activations Density 0.053%

    No Known Activations