© 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. 39831
    Prev
    Next
    INDEX
    Explanations

    basements and underground spaces

    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
     設置
    -1.45
     návr
    -1.45
    pozorn
    -1.42
    に行った
    -1.40
    瞜
    -1.38
    旆
    -1.37
    焄
    -1.35
     Courthouse
    -1.34
     détruit
    -1.33
     aérienne
    -1.31
    POSITIVE LOGITS
     is
    1.60
    。“
    1.58
    ྃ
    1.31
     bottom
    1.27
    ↵
    1.25
    「
    1.24
     below
    1.24
     of
    1.23
    Beschrijving
    1.23
     adat
    1.19
    Activations Density 0.004%

    No Known Activations