© 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. 12773
    Prev
    Next
    INDEX
    Explanations

    get the noun / find the noun

    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
     trovo
    -1.73
     pido
    -1.65
    The
    -1.65
    其他
    -1.64
    6
    -1.59
    hauled
    -1.59
     gelas
    -1.59
    鞮
    -1.59
    在自己
    -1.56
    8
    -1.55
    POSITIVE LOGITS
     them
    2.14
    ྂ
    1.61
    ୩
    1.57
     стене
    1.55
     been
    1.55
     Sometimes
    1.53
    𝗡
    1.53
    İN
    1.51
     δὲ
    1.48
     murky
    1.48
    Activations Density 0.126%

    No Known Activations