© 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. 1124
    Prev
    Next
    INDEX
    Explanations

    removable items

    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
     äta
    -2.39
     skriva
    -2.31
     säga
    -2.20
     However
    -2.13
     When
    -2.13
     arbeta
    -2.09
     lägga
    -2.06
    霂
    -2.05
     hjär
    -2.05
     tillgäng
    -2.05
    POSITIVE LOGITS
    臜
    2.75
     "
    2.73
    ブログ村
    2.36
    </strong>
    2.30
    ꦁ
    2.25
    おわりに
    2.23
    ?"
    2.23
    结语
    2.19
     be
    2.16
    ization
    2.13
    Activations Density 0.005%

    No Known Activations