© 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. 72843
    Prev
    Next
    INDEX
    Explanations

    route definitions and usage

    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
     perfekte
    -1.18
     loss
    -1.18
    stoffe
    -1.08
     lost
    -1.01
     tips
    -0.97
     hilfre
    -0.96
    wendige
    -0.95
     maler
    -0.94
    geen
    -0.93
    注重
    -0.92
    POSITIVE LOGITS
     navíc
    1.13
     Chriſt
    1.13
     layanan
    1.13
     TEA
    1.05
     particules
    1.05
    ător
    1.05
    }?
    1.04
     пирог
    1.04
    tempted
    1.02
     abaixo
    1.02
    Activations Density 0.042%

    No Known Activations