© 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. 38317
    Prev
    Next
    INDEX
    Explanations

    places and institutions

    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
     on
    -1.27
    cerea
    -1.09
    čet
    -1.05
     frische
    -1.02
     at
    -1.01
    ificance
    -0.99
    itives
    -0.98
    cheme
    -0.97
    してみて
    -0.96
     onPause
    -0.96
    POSITIVE LOGITS
    лябин
    0.96
     női
    0.94
     terce
    0.94
     jurk
    0.93
    Dosage
    0.92
    inerja
    0.91
    Substance
    0.91
     hiện
    0.91
     where
    0.90
     sapat
    0.90
    Activations Density 0.081%

    No Known Activations