© 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. 12665
    Prev
    Next
    INDEX
    Explanations

    acronyms

    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
    Still
    -2.25
    Another
    -2.13
    More
    -2.13
    ,
    -2.11
    Despite
    -2.00
    One
    -2.00
    Three
    -1.98
    \
    -1.97
    In
    -1.95
    There
    -1.95
    POSITIVE LOGITS
    琑
    2.31
    '\\
    2.14
    ].(
    2.06
    rsquo
    2.06
    :";
    2.05
    赑
    1.98
    
    1.98
    tsp
    1.96
     THOSE
    1.95
    嬭
    1.91
    Activations Density 0.181%

    No Known Activations