© 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. 79695
    Prev
    Next
    INDEX
    Explanations

    truck

    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
    ↵
    -2.73
    7
    -2.55
    TryDecode
    -2.42
    2
    -2.34
    4
    -2.30
    ཫ
    -2.23
    1
    -2.22
    ”.
    -2.13
    苼
    -2.13
      
    -2.11
    POSITIVE LOGITS
    UCIÓN
    2.64
    UCION
    2.31
    𓋼
    2.30
    ₂)
    2.23
    📞
    2.20
    ዡ
    2.17
    Ⅲ
    2.16
     These
    2.16
     Throwable
    2.14
    蕷
    2.13
    Activations Density 0.007%

    No Known Activations