© 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. 22-GEMMASCOPE-RES-131K
    7. 95393
    Prev
    Next
    INDEX
    Explanations

    if you for example

    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
    gimento
    -1.01
    Berat
    -0.99
    Дер
    -0.95
    wsze
    -0.94
    věr
    -0.91
    IMPLEMENT
    -0.91
     rekla
    -0.90
    mesine
    -0.89
     kerugian
    -0.89
     แต่
    -0.89
    POSITIVE LOGITS
     that
    2.13
     rằng
    1.24
    :
    1.23
    ;
    1.12
    ];
    1.02
    一旦
    0.97
     ofreciendo
    0.96
     certain
    0.94
     bahwa
    0.91
     gearbeitet
    0.91
    Activations Density 0.051%

    No Known Activations