© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 54056
    Prev
    Next
    INDEX
    Explanations

    laws and constitutions

    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
     afast
    -1.16
    Kapcsolódó
    -0.98
     ufficiale
    -0.96
     (!__
    -0.94
    𝒗
    -0.94
     didn
    -0.91
    atify
    -0.91
     mitigate
    -0.91
    bitan
    -0.91
     heureuse
    -0.90
    POSITIVE LOGITS
    篮
    1.12
     åren
    1.06
    蹿
    1.05
     språk
    1.01
     Прези
    0.99
    👁
    0.96
    🎟
    0.94
     suéter
    0.93
     regeringen
    0.93
    čios
    0.93
    Activations Density 0.020%

    No Known Activations