© 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. 61257
    Prev
    Next
    INDEX
    Explanations

    password in code

    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
     your
    -1.38
     any
    -1.27
     all
    -1.27
    鍗
    -1.23
    ⤿
    -1.21
    Зноскі
    -1.20
    了出去
    -1.19
    ()=>{
    -1.13
     vivía
    -1.10
     ημέ
    -1.10
    POSITIVE LOGITS
    으로
    1.15
     هذه
    1.09
    maxSize
    1.05
    [
    1.03
    $$
    1.00
    utando
    0.99
     $
    0.98
    非常に
    0.98
    setImageBitmap
    0.98
    ümü
    0.97
    Activations Density 0.018%

    No Known Activations