© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 128443
    Prev
    Next
    INDEX
    Explanations

    variables and code structures

    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_22/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
     and
    -1.87
    !=-
    -1.05
     فور
    -1.04
    のお客様
    -1.04
     greece
    -1.00
    tifications
    -0.99
    urnya
    -0.97
     kilo
    -0.96
    化する
    -0.94
    “,
    -0.94
    POSITIVE LOGITS
     other
    1.38
    があります
    0.98
    がありますが
    0.96
     méthode
    0.94
    実感
    0.93
     idea
    0.92
    ジナル
    0.91
    參考文獻
    0.91
     itself
    0.91
    けれ
    0.91
    Activations Density 0.115%

    No Known Activations