© 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. 57404
    Prev
    Next
    INDEX
    Explanations

    technical terms and entities

    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
     there
    -1.28
    THERS
    -1.15
    籥
    -1.08
     it
    -1.08
     scrutin
    -1.05
    дения
    -1.04
    ប
    -0.99
    だったら
    -0.98
     Economía
    -0.98
    𝕨
    -0.98
    POSITIVE LOGITS
     поэтому
    1.27
     gespannt
    1.13
    ὸ
    1.13
     будем
    1.13
     perdiendo
    1.12
     लेकिन
    1.09
    }.
    1.07
     their
    1.06
    为啥
    1.06
     quindi
    1.03
    Activations Density 0.354%

    No Known Activations