© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 65901
    Prev
    Next
    INDEX
    Explanations

    related to categories

    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_34/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
     if
    -1.26
     that
    -1.06
    無し
    -1.04
     before
    -1.02
     pilih
    -0.99
    komme
    -0.96
     puts
    -0.94
    にしました
    -0.94
     idiomas
    -0.93
     terkena
    -0.93
    POSITIVE LOGITS
    na
    1.07
     reiterated
    1.04
    nade
    1.04
    le
    1.03
     debacle
    1.02
    k
    1.01
    ‌.
    1.01
    なので
    1.00
     fiasco
    0.98
    という
    0.98
    Activations Density 0.002%

    No Known Activations