© 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. 117999
    Prev
    Next
    INDEX
    Explanations

    opening

    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
     downloadable
    -0.81
    块钱
    -0.71
     overheard
    -0.71
     ständig
    -0.69
    لينكات
    -0.68
     skon
    -0.66
     Nugent
    -0.66
     Abschluss
    -0.66
    тература
    -0.65
    aris
    -0.64
    POSITIVE LOGITS
     opening
    3.39
     opened
    3.38
    Opening
    2.84
     unwra
    2.78
    opening
    2.70
    opened
    2.66
     Opening
    2.63
     opens
    2.61
    打开
    2.55
    Opened
    2.52
    Activations Density 0.059%

    No Known Activations