© 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. 13492
    Prev
    Next
    INDEX
    Explanations

    questions starting with "do you"

    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
    -2.63
    は
    -2.55
    4
    -2.53
    訁
    -2.50
    5
    -2.36
     Erfol
    -2.31
     The
    -2.28
     ที่
    -2.22
    也
    -2.22
    是
    -2.16
    POSITIVE LOGITS
     centavos
    2.39
     analisis
    2.28
     itens
    2.27
    ⃚
    2.25
    😲
    2.20
     sena
    2.17
     algorit
    2.17
     zis
    2.16
     porcent
    2.14
     vivas
    2.13
    Activations Density 0.017%

    No Known Activations