© 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. 117168
    Prev
    Next
    INDEX
    Explanations

    Unity script settings

    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
     transforms
    -0.92
     position
    -0.86
     world
    -0.82
     transform
    -0.82
    Vector
    -0.82
    Vec
    -0.80
     Vec
    -0.77
    Transform
    -0.76
     Vector
    -0.75
     Diptera
    -0.75
    POSITIVE LOGITS
     plugin
    0.83
    Další
    0.80
    hibitor
    0.79
     Mathf
    0.77
    ADVERTISEMENT
    0.75
    Qualification
    0.74
     enää
    0.73
    PlayerPrefs
    0.72
    Plugin
    0.70
     jäl
    0.70
    Activations Density 0.054%

    No Known Activations