© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26921
    Prev
    Next
    INDEX
    Explanations

    recommendations and imperatives

    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
     intended
    -1.07
    quela
    -1.05
     Still
    -1.01
     später
    -1.01
     effectively
    -0.98
     resulting
    -0.98
    这下
    -0.94
     could
    -0.94
     purpose
    -0.92
     primarily
    -0.92
    POSITIVE LOGITS
     если
    1.36
     włosów
    1.21
     обязательно
    1.21
     اگر
    1.20
    如果
    1.18
    erializer
    1.16
     accordé
    1.16
     unbedingt
    1.16
     suoi
    1.13
    至少
    1.13
    Activations Density 0.018%

    No Known Activations