© 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. 34-GEMMASCOPE-RES-131K
    7. 116790
    Prev
    Next
    INDEX
    Explanations

    See accompanying file

    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_34/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
    （
    -1.06
     (
    -1.05
    ')){
    -0.94
    ！（
    -0.90
    مكن
    -0.87
     />}
    -0.83
    нти
    -0.82
    '],
    -0.81
    (){
    -0.81
    لیسی
    -0.80
    POSITIVE LOGITS
    )
    2.88
     '')
    1.95
    ).
    1.94
     {})
    1.94
    )
    1.90
     "")
    1.89
    ?)
    1.74
    )\
    1.73
     [])
    1.59
    )\\
    1.56
    Activations Density 0.426%

    No Known Activations