© 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. 10-GEMMASCOPE-RES-131K
    4. 48166
    Prev
    Next
    INDEX
    Explanations

    mapper, mailer, harp, afterEach

    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_10/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
    </h3>
    -3.61
    
    -2.44
    "));
    -2.36
    </strong>
    -2.33
    ";
    -2.31
     This
    -2.27
     tenido
    -2.22
     avec
    -2.20
    放入
    -2.11
    </sub>
    -2.09
    POSITIVE LOGITS
    琑
    2.73
    </b>
    2.70
    ༑
    2.17
    Ⲉ
    2.09
    皷
    2.06
    mapper
    2.03
    Ἦ
    2.02
     использовать
    1.98
    wanzig
    1.97
     ________
    1.96
    Activations Density 0.001%

    No Known Activations