© 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. 10-GEMMASCOPE-RES-131K
    7. 19778
    Prev
    Next
    INDEX
    Explanations

    threat

    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_10/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
    刧
    -2.53
    ()))
    -2.50
    ଽ
    -2.47
    rierten
    -2.44
    女性の
    -2.39
     土産
    -2.34
    苳
    -2.30
    以上です
    -2.27
    ).”
    -2.27
    　　（
    -2.27
    POSITIVE LOGITS
     is
    3.23
    
    3.06
    .
    2.91
    咴
    2.52
    餍
    2.47
    But
    2.41
     They
    2.41
    0
    2.39
     notwendi
    2.39
     -----
    2.39
    Activations Density 0.005%

    No Known Activations