© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66807
    Prev
    Next
    INDEX
    Explanations

    events and 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
    了一眼
    -1.14
     devrez
    -1.10
    RotationOrder
    -1.05
     presently
    -1.03
     quoc
    -1.02
    今は
    -1.01
     stijl
    -0.98
    HideFlags
    -0.96
    yaretçi
    -0.94
     bershka
    -0.94
    POSITIVE LOGITS
     last
    1.23
     when
    1.21
     primeiros
    1.07
    筱
    1.05
     When
    1.04
     first
    1.00
     csak
    1.00
    最初の
    0.97
     began
    0.96
     Each
    0.96
    Activations Density 0.034%

    No Known Activations