© 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. 8841
    Prev
    Next
    INDEX
    Explanations

    URLs and technical terms

    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
    pantalon
    -1.64
    Ça
    -1.47
     to
    -1.47
     establecidos
    -1.45
     consequent
    -1.44
     aislados
    -1.42
     involucrados
    -1.40
     škoda
    -1.39
    langsung
    -1.39
    Theft
    -1.37
    POSITIVE LOGITS
    begin
    1.63
     zostały
    1.48
     such
    1.45
     here
    1.37
     متحده
    1.36
    𝐲
    1.35
    ."
    1.31
     we
    1.30
                
    1.28
     UserDao
    1.28
    Activations Density 0.001%

    No Known Activations