© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13391
    Prev
    Next
    INDEX
    Explanations

    questions and introductory phrases

    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
     of
    -1.63
     enga
    -1.20
     oggi
    -1.07
    的目光
    -1.06
     his
    -1.05
    Nowadays
    -1.01
     Aver
    -1.01
     he
    -1.00
    тися
    -1.00
    IntPtr
    -0.98
    POSITIVE LOGITS
     or
    1.49
     máscaras
    1.48
     ботинки
    1.27
     няколко
    1.27
     poteva
    1.25
     estructuras
    1.19
     solche
    1.16
     desmotiv
    1.13
     domésticos
    1.12
     такая
    1.10
    Activations Density 0.360%

    No Known Activations