© 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. 1147
    Prev
    Next
    INDEX
    Explanations

    Marcel, fstream, Biden, markedly

    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
    !”
    -3.52
    !)
    -2.63
    </sup>
    -2.59
     extravagant
    -2.58
    ｙ
    -2.55
    ！”
    -2.42
    ꠥ
    -2.38
     After
    -2.31
     extraordinarily
    -2.27
    西北
    -2.27
    POSITIVE LOGITS
     they
    2.86
     enfati
    2.80
    筇
    2.56
    鷽
    2.55
    鼉
    2.52
    ’
    2.50
    蟶
    2.48
    called
    2.44
    棡
    2.41
     butik
    2.39
    Activations Density 0.002%

    No Known Activations