© 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. 34-GEMMASCOPE-RES-131K
    7. 34932
    Prev
    Next
    INDEX
    Explanations

    closing code delimiters

    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_34/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
    翻攝
    -1.02
    指摘
    -1.02
     there
    -1.00
    YLON
    -0.90
    除此之外
    -0.90
     ebenso
    -0.88
    tux
    -0.88
    FormComponent
    -0.87
    __':
    -0.87
    委员
    -0.87
    POSITIVE LOGITS
     Colegio
    1.00
    ņas
    0.96
    ↵
    0.95
    stes
    0.90
     provoquer
    0.88
     africains
    0.88
     garantit
    0.87
     peindre
    0.87
     renforcer
    0.85
    TAM
    0.84
    Activations Density 0.022%

    No Known Activations