© 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. 129499
    Prev
    Next
    INDEX
    Explanations

    decides, chooses, influences actions or outcomes

    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
     DialogInterface
    -1.10
    romole
    -0.96
     aquele
    -0.96
    чя
    -0.95
    олові
    -0.93
    endwhile
    -0.91
    谑
    -0.90
    ocia
    -0.90
    Ỹ
    -0.90
     eş
    -0.88
    POSITIVE LOGITS
     decides
    1.84
     decisions
    1.84
     deciding
    1.77
    决定
    1.73
     decide
    1.67
     decision
    1.54
    決定
    1.46
     decidir
    1.42
     decidi
    1.37
     who
    1.31
    Activations Density 0.033%

    No Known Activations