© 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. 22-GEMMASCOPE-RES-131K
    7. 32990
    Prev
    Next
    INDEX
    Explanations

    links, directness, and conversion

    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
     Dicapai
    -0.94
    écial
    -0.81
    przed
    -0.81
     accepte
    -0.80
     Meksiko
    -0.79
     guitarra
    -0.78
    LatLng
    -0.78
     camion
    -0.77
    兴趣
    -0.77
    atorial
    -0.77
    POSITIVE LOGITS
     correlation
    1.27
     directly
    1.27
     conversion
    1.16
    conversion
    1.15
    直接
    1.10
     direct
    1.09
    direct
    1.09
     Directly
    1.02
     linking
    1.02
     connection
    1.01
    Activations Density 0.217%

    No Known Activations