© 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. 128205
    Prev
    Next
    INDEX
    Explanations

    how something happens or is determined

    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
     telah
    -1.04
     đã
    -0.95
     varones
    -0.94
    νομα
    -0.94
    minen
    -0.93
    TRIBUN
    -0.93
     sûre
    -0.92
    irme
    -0.92
    minipage
    -0.91
    それでは
    -0.90
    POSITIVE LOGITS
     how
    1.64
     whether
    1.33
     direction
    1.20
     choice
    1.20
     outcome
    1.17
     determine
    1.16
     overall
    1.13
     what
    1.09
     shape
    1.07
     ultimately
    1.05
    Activations Density 0.156%

    No Known Activations