© 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. 39373
    Prev
    Next
    INDEX
    Explanations

    markdown and code structures

    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
     its
    -1.09
    corrhi
    -1.05
    GetAxis
    -1.04
     this
    -1.03
    digitalWrite
    -1.03
    тное
    -1.02
     have
    -1.02
     specifies
    -1.01
    ！】
    -1.01
     meticulously
    -0.98
    POSITIVE LOGITS
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.06
     hilfiger
    1.04
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.03
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.00
    ↵↵↵↵↵↵↵↵↵↵↵
    0.95
     contextLoads
    0.94
     russian
    0.93
    ovo
    0.93
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.92
    ely
    0.92
    Activations Density 0.001%

    No Known Activations