© 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. 40225
    Prev
    Next
    INDEX
    Explanations

    integrals over intervals `[a,b]`

    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
     диамет
    -1.20
    靭
    -1.07
     презента
    -1.05
    靱
    -1.03
    erintah
    -1.02
     квітня
    -0.94
     ドラゴン
    -0.93
     Bakterien
    -0.92
     токси
    -0.92
    ]!=
    -0.91
    POSITIVE LOGITS
     disintegration
    1.00
     美国
    0.98
     člán
    0.93
     экономических
    0.92
    estos
    0.91
    攫
    0.91
     especializada
    0.91
     these
    0.90
    vincible
    0.88
    rehensive
    0.88
    Activations Density 0.029%

    No Known Activations