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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 12223
    Prev
    Next
    INDEX
    Explanations

    variable declarations

    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
     RouterModule
    -0.89
     nombreux
    -0.84
     muitos
    -0.84
     Allí
    -0.84
    队的
    -0.82
     puisque
    -0.82
     Aunque
    -0.81
    iteľ
    -0.81
     Estos
    -0.80
     Parmi
    -0.80
    POSITIVE LOGITS
     mapStateToProps
    1.56
     styles
    1.23
     forstå
    1.09
     særlig
    1.02
     initially
    0.97
     sizes
    0.97
     настолько
    0.96
     in
    0.96
    懨
    0.94
     criteria
    0.94
    Activations Density 0.008%

    No Known Activations