© 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. 10-GEMMASCOPE-RES-131K
    4. 39123
    Prev
    Next
    INDEX
    Explanations

    GMT timestamps

    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_10/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
     and
    -1.84
    ...)
    -1.58
    ):
    
    -1.55
    ?」
    -1.51
    ?)
    -1.46
     tym
    -1.41
    ...),
    -1.41
     новой
    -1.40
     
    -1.38
    ?”
    -1.38
    POSITIVE LOGITS
    </h2>
    1.56
     '';
    1.51
    Ute
    1.45
    Mardi
    1.39
    никами
    1.39
     dichotomy
    1.37
     glimmer
    1.36
    Tener
    1.34
    ganggu
    1.33
     gydy
    1.32
    Activations Density 0.003%

    No Known Activations