© 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. 70347
    Prev
    Next
    INDEX
    Explanations

    amazon references

    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
    );//
    -2.70
    分明
    -2.47
     nuovi
    -2.33
    ];
    -2.25
    鹮
    -2.20
    ');
    -2.19
    有大
    -2.11
     dejected
    -2.09
     diarios
    -2.06
    많
    -2.06
    POSITIVE LOGITS
    ↵↵
    3.14
    {
    2.33
     我们
    2.28
    甞
    2.20
     We
    2.11
     besar
    1.93
    ardige
    1.85
    ༵
    1.82
     seventeen
    1.81
    萣
    1.80
    Activations Density 0.010%

    No Known Activations