© 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. 42360
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
     then
    -1.46
     nii
    -1.35
    💅
    -1.18
    !（
    -1.18
    !».
    -1.16
    💁
    -1.15
     by
    -1.15
     XXXII
    -1.13
    ;?
    -1.13
    fucker
    -1.12
    POSITIVE LOGITS
     of
    1.35
     
    1.23
     dégâts
    1.12
     estremamente
    1.11
     حوالي
    1.07
    𝓑
    1.06
     Evaluating
    1.05
    Regarding
    1.05
     Regarding
    1.04
    Selecting
    1.04
    Activations Density 0.038%

    No Known Activations