© 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. 9785
    Prev
    Next
    INDEX
    Explanations

    dependency injection and inversion

    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
     rosse
    -2.50
     meravigli
    -2.44
    怱
    -2.39
    扨
    -2.30
     assolutamente
    -2.23
    孥
    -2.23
    ar
    -2.22
    ︕
    -2.22
     rossa
    -2.20
     bellissimo
    -2.17
    POSITIVE LOGITS
    ’
    2.97
    ↵
    2.92
    i
    2.81
    ↵↵↵↵↵↵↵↵↵↵
    2.45
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    2.41
     моя
    2.39
    ↵↵↵↵↵↵↵↵↵↵↵↵
    2.22
    ↵↵↵↵↵↵↵↵↵↵↵
    2.13
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    2.13
    ↵↵↵↵↵↵↵↵
    2.11
    Activations Density 0.023%

    No Known Activations