© 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. 80820
    Prev
    Next
    INDEX
    Explanations

    exclamations starting with "Oh"

    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
    when
    -3.14
    S
    -2.81
     และ
    -2.64
    these
    -2.63
    by
    -2.55
    >
    -2.48
    зации
    -2.45
    ”),
    -2.45
     パターン
    -2.33
    臜
    -2.31
    POSITIVE LOGITS
    }
    2.63
    s
    2.61
    ꜆
    2.56
    ᠌
    2.56
     l
    2.53
    能在
    2.31
     
    2.22
    狁
    2.17
     homage
    2.16
     mindful
    2.16
    Activations Density 0.011%

    No Known Activations