© 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. 72286
    Prev
    Next
    INDEX
    Explanations

    code blocks with `)` or `()`

    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
     förra
    -1.01
     viena
    -0.94
    addProperty
    -0.88
     gamla
    -0.88
    DeclareMath
    -0.87
    []>(
    -0.85
    相处
    -0.85
     ventilador
    -0.85
     högre
    -0.84
    کتور
    -0.82
    POSITIVE LOGITS
     then
    1.33
     if
    1.10
     потом
    0.98
     hasilnya
    0.98
    แล้ว
    0.97
     THEN
    0.96
     Finished
    0.90
    ราบ
    0.89
     тогда
    0.87
    鱻
    0.87
    Activations Density 0.006%

    No Known Activations