© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44162
    Prev
    Next
    INDEX
    Explanations

    explorers and expeditions

    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
    >
    -1.64
     deportistas
    -1.35
    
    -1.33
    ра
    -1.30
    Ꮺ
    -1.30
     например
    -1.28
     /
    -1.28
    んでも
    -1.27
    ).
    -1.23
     delincuentes
    -1.22
    POSITIVE LOGITS
    UCIÓN
    1.55
     ...
    1.45
    口气
    1.32
     to
    1.31
    ATES
    1.29
     artistico
    1.27
     sekitarnya
    1.27
    性は
    1.26
     Compared
    1.25
     ricco
    1.24
    Activations Density 0.045%

    No Known Activations