© 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. 30874
    Prev
    Next
    INDEX
    Explanations

    EmberJS code and documentation

    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
    čnih
    -0.90
    dieux
    -0.90
     Haryana
    -0.87
     Fiji
    -0.80
    Източници
    -0.79
    둑
    -0.78
    ็ต
    -0.77
     Thames
    -0.77
    就行
    -0.76
     partnered
    -0.76
    POSITIVE LOGITS
     Ember
    1.36
    ember
    1.27
    Ember
    1.20
    Wisconsin
    1.19
     Wisconsin
    1.19
    Milwaukee
    1.19
     Milwaukee
    1.15
     ember
    1.13
     RSVP
    0.85
     Packers
    0.84
    Activations Density 0.028%

    No Known Activations