© 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. 71411
    Prev
    Next
    INDEX
    Explanations

    code and non-English titles

    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
    おわりに
    -1.30
    総評
    -1.05
    さっき
    -1.04
    もうすぐ
    -1.04
    おまけ
    -1.03
    Nguồn
    -1.02
     erbjud
    -1.01
    ツイッター
    -1.01
    本当の
    -1.00
    手軽
    -0.98
    POSITIVE LOGITS
     CLASS
    1.11
    踪
    1.10
    Ì
    1.02
    }}_{
    0.98
    @[+][
    0.97
    banez
    0.96
    )":
    0.96
    ))),
    0.94
    moiselle
    0.94
     rasgos
    0.94
    Activations Density 0.056%

    No Known Activations