© 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. 70526
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation leading to specific terms

    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
    鄧
    -1.08
     sebagainya
    -1.05
     marvellous
    -1.02
    ⁦
    -1.00
     Tells
    -0.98
    ⇢
    -0.96
     vélos
    -0.95
     نهایت
    -0.95
     Grundstück
    -0.95
     教室
    -0.95
    POSITIVE LOGITS
     we
    1.25
     MotionEvent
    1.23
     there
    1.16
     to
    1.16
     communiquez
    1.06
     they
    1.05
    完成です
    1.05
     descripción
    1.00
    而在
    1.00
    也不是
    1.00
    Activations Density 0.000%

    No Known Activations