© 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. 36642
    Prev
    Next
    INDEX
    Explanations

    Spring Boot configuration

    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
    SequentialGroup
    -1.15
    了一会儿
    -1.13
    *************/
    -1.09
    США
    -1.09
    oulos
    -1.06
    栳
    -1.05
     prision
    -1.02
    Legături
    -0.99
     alcoh
    -0.98
     MethodInfo
    -0.97
    POSITIVE LOGITS
     asimismo
    0.97
     reconoci
    0.96
     inmigrantes
    0.93
     and
    0.92
     embaraz
    0.88
     ejerc
    0.88
     home
    0.87
     universitarios
    0.85
     nacidos
    0.84
     במ
    0.84
    Activations Density 0.001%

    No Known Activations