© 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. 34-GEMMASCOPE-RES-131K
    7. 79184
    Prev
    Next
    INDEX
    Explanations

    various word beginnings

    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_34/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
    手の
    -0.68
    (<
    -0.68
     πε
    -0.68
     Sally
    -0.68
    ête
    -0.67
     Theorems
    -0.67
     яр
    -0.66
    viers
    -0.66
     hoặc
    -0.65
     համ
    -0.65
    POSITIVE LOGITS
     UITableView
    0.75
     λειτουργ
    0.73
    UNES
    0.71
    Hace
    0.71
    Shaun
    0.70
     pitié
    0.70
    hoea
    0.69
     lados
    0.69
     Shaun
    0.68
    Funktion
    0.68
    Activations Density 0.039%

    No Known Activations