© 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. 66560
    Prev
    Next
    INDEX
    Explanations

    export default declarations

    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
     других
    -1.14
    による
    -1.10
     collect
    -1.03
     know
    -1.01
    特典
    -0.99
     睡
    -0.99
     柜
    -0.99
     innych
    -0.98
     l
    -0.97
     孩子
    -0.97
    POSITIVE LOGITS
    voorbeeld
    1.38
    izados
    1.25
     theſe
    1.18
     ſon
    1.13
    verhältnisse
    1.13
    []
    1.09
    çade
    1.09
    ↓↓↓
    1.08
     inclusief
    1.08
    潜力
    1.07
    Activations Density 0.003%

    No Known Activations