© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 128458
    Prev
    Next
    INDEX
    Explanations

    named persons and their roles

    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
    Obrázky
    -1.14
     tradis
    -1.09
     reiz
    -1.09
     kraf
    -1.05
     dansk
    -1.05
     institucional
    -1.05
     nya
    -1.05
    :@
    -1.04
     favoris
    -1.04
     so
    -1.04
    POSITIVE LOGITS
     a
    1.27
    /*!
    
    1.19
     (!__
    1.15
     bairro
    1.13
    ji
    1.10
     renegade
    1.09
    inely
    1.09
     desenvolvimento
    1.08
    ご理解
    1.07
     zumindest
    1.06
    Activations Density 0.000%

    No Known Activations