© 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. 57089
    Prev
    Next
    INDEX
    Explanations

    inward and outward directions

    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
    EXIT
    -0.98
    上下
    -0.85
     Exit
    -0.85
     exit
    -0.84
    Incre
    -0.81
    Exit
    -0.80
    exit
    -0.78
    の上
    -0.72
     há
    -0.70
    offs
    -0.69
    POSITIVE LOGITS
     inward
    4.69
     inwards
    4.06
     inwardly
    2.72
    内
    2.03
     inbound
    2.02
     outward
    1.98
     внут
    1.85
    inbound
    1.74
     outwards
    1.72
    內
    1.71
    Activations Density 0.065%

    No Known Activations