© 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. 71832
    Prev
    Next
    INDEX
    Explanations

    counts and quantities

    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
     while
    -1.20
     one
    -1.14
     or
    -1.14
     hvordan
    -1.01
     suyu
    -0.98
     as
    -0.96
     three
    -0.96
     two
    -0.94
     \
    -0.89
     specific
    -0.89
    POSITIVE LOGITS
     даже
    1.16
     ursprüng
    1.09
     deixou
    1.05
    睏
    1.04
     majú
    1.01
     ktoré
    1.00
     heutige
    1.00
     gráficos
    1.00
     ภาพ
    0.99
    actrice
    0.99
    Activations Density 0.010%

    No Known Activations