© 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. 22-GEMMASCOPE-RES-131K
    7. 128621
    Prev
    Next
    INDEX
    Explanations

    detects import statements

    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
    放題
    -1.07
    SESSION
    -1.02
     ComVisible
    -1.01
     Verk
    -1.01
    ToObject
    -0.95
    –¿
    -0.94
    Especificações
    -0.94
    drawImage
    -0.92
    ataires
    -0.91
    了一会儿
    -0.90
    POSITIVE LOGITS
    人で
    1.06
    뭘
    1.05
     стимули
    1.03
    あー
    1.02
     residuos
    1.00
    何度も
    1.00
     expectation
    0.98
    だいたい
    0.97
     getestet
    0.96
    ługi
    0.95
    Activations Density 0.005%

    No Known Activations