© 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. 22-GEMMASCOPE-RES-131K
    7. 130946
    Prev
    Next
    INDEX
    Explanations

    legal texts about justice

    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
     吗
    -0.86
     owo
    -0.84
    ֿ
    -0.83
    machten
    -0.83
    __',
    -0.83
     nke
    -0.83
    ЩЕ
    -0.82
    psc
    -0.82
    ابي
    -0.82
     dudes
    -0.82
    POSITIVE LOGITS
     wichtigen
    1.06
     zostanie
    1.05
     actuales
    1.05
     różnych
    1.02
     dingen
    1.01
    これも
    1.00
    こちらも
    0.99
    様に
    0.98
     также
    0.98
    9
    0.97
    Activations Density 0.001%

    No Known Activations