© 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. 119904
    Prev
    Next
    INDEX
    Explanations

    tax, house, politics, train, card, astronomy

    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
     of
    -2.33
     []:
    -1.63
    ‚¬
    -1.52
    )="
    -1.50
    }_{
    -1.48
    inWeight
    -1.45
    )}
    
    -1.45
    )}$,
    -1.41
    </>
    
    -1.41
     {
    
    
    -1.41
    POSITIVE LOGITS
    7
    1.59
     for
    1.45
     their
    1.37
     Ironically
    1.34
     Their
    1.34
    設施
    1.32
    Hanya
    1.27
    8
    1.27
     thật
    1.27
    5
    1.27
    Activations Density 0.203%

    No Known Activations