© 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. 11182
    Prev
    Next
    INDEX
    Explanations

    among lists

    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
     just
    -0.98
     all
    -0.97
     либо
    -0.95
    arna
    -0.90
    Ṛ
    -0.87
    runOnUiThread
    -0.84
    maksi
    -0.83
    ]',
    -0.82
    enciado
    -0.82
     Although
    -0.82
    POSITIVE LOGITS
     include
    2.39
     includes
    2.17
     incluye
    1.82
     incluyen
    1.77
     included
    1.77
    includes
    1.63
    include
    1.59
     inclui
    1.55
    包括
    1.53
     includ
    1.51
    Activations Density 0.049%

    No Known Activations