© 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. 13806
    Prev
    Next
    INDEX
    Explanations

    programming language keywords

    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
    arnya
    -1.59
    terse
    -1.56
     feltro
    -1.55
    REEK
    -1.53
     dezelve
    -1.52
    parfum
    -1.51
     唯美
    -1.48
    geç
    -1.48
     pneus
    -1.43
     vinil
    -1.42
    POSITIVE LOGITS
    e
    1.49
    on
    1.45
    T
    1.41
    al
    1.38
    )
    1.38
    O
    1.38
    뭘
    1.38
    J
    1.36
    P
    1.35
    to
    1.33
    Activations Density 0.074%

    No Known Activations