© 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. 22-GEMMASCOPE-RES-131K
    7. 27082
    Prev
    Next
    INDEX
    Explanations

    way to a destination

    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_22/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
     moeite
    -1.05
    despite
    -1.02
     teníamos
    -1.00
     geweldig
    -0.96
     uitge
    -0.94
     tuvimos
    -0.94
    still
    -0.94
     fijn
    -0.91
     wyjątk
    -0.91
     vẫn
    -0.91
    POSITIVE LOGITS
     better
    1.27
     ultimately
    1.25
     eventually
    1.13
     achieve
    1.07
     bigger
    1.05
     quicker
    1.03
     Ultimately
    1.02
    werb
    1.00
     deeper
    0.98
     eventual
    0.98
    Activations Density 0.073%

    No Known Activations