© 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. 69167
    Prev
    Next
    INDEX
    Explanations

    legal case citations

    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
     and
    -1.61
     who
    -1.46
     pengiriman
    -1.45
     nawet
    -1.45
     this
    -1.43
     pintu
    -1.38
     harga
    -1.36
     технологий
    -1.35
     biaya
    -1.35
    )):
    -1.34
    POSITIVE LOGITS
    ]
    1.66
     delà
    1.38
     malheur
    1.36
    {
    1.34
    -
    1.28
     Not
    1.27
     shes
    1.20
    TE
    1.16
     pouvaient
    1.14
    ,
    1.14
    Activations Density 0.030%

    No Known Activations