© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72453
    Prev
    Next
    INDEX
    Explanations

    must or need to do

    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
    ينو
    -1.52
    Generally
    -1.38
    Typically
    -1.33
    تصویر
    -1.32
    کاربرد
    -1.30
     сообщил
    -1.30
     muualla
    -1.27
    侷
    -1.27
    Usually
    -1.27
     ribuan
    -1.26
    POSITIVE LOGITS
     it
    1.83
     to
    1.52
    它
    1.43
    chnung
    1.35
     what
    1.35
     again
    1.27
    cipitation
    1.27
     now
    1.24
    owels
    1.23
     nothing
    1.21
    Activations Density 0.197%

    No Known Activations