© 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. 27492
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis and sql schema definitions

    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
    \<
    -1.01
    🙌
    -1.01
     to
    -0.94
    -------------</
    -0.94
     cewek
    -0.93
     绘画
    -0.93
     மற்றும்
    -0.91
    $_,
    -0.91
    量的
    -0.90
     INFORMACIÓN
    -0.89
    POSITIVE LOGITS
     lesquels
    0.94
     menjalankan
    0.91
     обязательно
    0.90
    
    0.90
    erobic
    0.89
    ใคร
    0.88
    äksi
    0.87
     airfield
    0.85
    Ирина
    0.85
     invitamos
    0.85
    Activations Density 0.004%

    No Known Activations