© 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. 22-GEMMASCOPE-RES-131K
    4. 12804
    Prev
    Next
    INDEX
    Explanations

    beginning of technical descriptions

    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
    現代
    -0.94
    𝗕
    -0.94
     egens
    -0.94
    tagHelperRunner
    -0.93
    GOTREF
    -0.88
    HET
    -0.87
     unnoticed
    -0.87
    čů
    -0.87
     engelsk
    -0.85
     perfecte
    -0.85
    POSITIVE LOGITS
    了下去
    0.96
     あります
    0.93
    🕗
    0.87
    istically
    0.87
     также
    0.86
    くな
    0.84
    est
    0.83
     daraus
    0.82
    artner
    0.81
    ĸ
    0.81
    Activations Density 0.001%

    No Known Activations