© 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. 34-GEMMASCOPE-RES-131K
    7. 750
    Prev
    Next
    INDEX
    Explanations

    header files and code generation

    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
    ciera
    -0.98
     prøve
    -0.96
    Slik
    -0.84
    ionization
    -0.82
     informasi
    -0.82
     центр
    -0.82
     Blon
    -0.81
     sikre
    -0.79
     følgende
    -0.79
    hira
    -0.79
    POSITIVE LOGITS
     utter
    0.94
     rubrique
    0.91
    __["
    0.83
     finally
    0.83
    jemahan
    0.82
    𝑪
    0.81
     Bapak
    0.81
     Comcast
    0.79
     إذ
    0.77
     Alexey
    0.77
    Activations Density 0.001%

    No Known Activations