© 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. 34-GEMMASCOPE-RES-131K
    4. 87303
    Prev
    Next
    INDEX
    Explanations

    numbered or lettered lists followed by parentheses

    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
    omyces
    -0.78
    sufficiency
    -0.75
    inistro
    -0.75
    !(
    -0.74
    Compass
    -0.71
    IMG
    -0.71
     kampen
    -0.70
    zupeł
    -0.69
     ledig
    -0.68
     []:
    -0.67
    POSITIVE LOGITS
    )
    2.73
    ))
    2.19
    )
    1.94
    })
    1.82
    )-
    1.81
     )
    1.73
    ),
    1.66
    )
    
    1.60
    ())
    1.54
    )$
    1.49
    Activations Density 0.081%

    No Known Activations