© 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. 15536
    Prev
    Next
    INDEX
    Explanations

    instead or rather

    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
    ൾ
    -0.91
     régiment
    -0.90
    ությ
    -0.88
     Irish
    -0.88
     sekal
    -0.88
     geschehen
    -0.85
    轮回
    -0.79
     any
    -0.79
     maupun
    -0.78
    amable
    -0.77
    POSITIVE LOGITS
     instead
    1.98
    Instead
    1.53
    instead
    1.52
     вместо
    1.48
     zamiast
    1.26
     Instead
    1.13
     invece
    1.13
     místo
    1.01
    statt
    0.95
     rather
    0.93
    Activations Density 0.028%

    No Known Activations