© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74366
    Prev
    Next
    INDEX
    Explanations

    current time

    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
     with
    -2.02
     from
    -1.98
     Mulai
    -1.75
     Setelah
    -1.68
     originalen
    -1.67
     Pemain
    -1.66
     Meski
    -1.65
     丁目
    -1.63
     Membuat
    -1.62
     when
    -1.61
    POSITIVE LOGITS
    currently
    1.47
     ingenieros
    1.39
    悪魔
    1.39
     compró
    1.38
    想法
    1.36
     \
    1.34
    biendo
    1.34
     renovables
    1.34
    プライ
    1.34
     prácti
    1.34
    Activations Density 0.065%

    No Known Activations