© 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. 9584
    Prev
    Next
    INDEX
    Explanations

    2, TH, this, quit, or punctuation

    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
     móg
    -1.09
    奬
    -1.05
    🏓
    -1.02
    знание
    -1.01
     altavoz
    -1.01
    見えます
    -0.98
     তারিখ
    -0.98
     zwi
    -0.98
    黜
    -0.96
    Ϊ
    -0.96
    POSITIVE LOGITS
     but
    1.29
     example
    1.18
     use
    1.16
     uses
    1.05
     examples
    0.99
    AMIENTO
    0.99
    ↵↵
    0.98
     test
    0.98
    ísica
    0.97
    bardziej
    0.97
    Activations Density 0.011%

    No Known Activations