© 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. 73041
    Prev
    Next
    INDEX
    Explanations

    preposition + word

    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
    ",
    -1.38
    </i>
    -1.28
    <bos>
    -1.24
    なども
    -1.20
    러한
    -1.16
    ıştı
    -1.14
    ↵↵↵
    -1.13
    ("|
    -1.13
    upyter
    -1.12
    礎
    -1.12
    POSITIVE LOGITS
    сль
    1.37
    поги
    1.20
    ffling
    1.17
     sinnvoll
    1.16
    ніе
    1.15
    力
    1.15
    heureux
    1.14
    aysia
    1.14
    torem
    1.14
     Город
    1.13
    Activations Density 0.602%

    No Known Activations