© 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. 103602
    Prev
    Next
    INDEX
    Explanations

    closing parentheses and quotes

    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
    "].
    -1.21
    ].
    -0.98
    }$\\
    -0.89
    '].
    -0.87
     appears
    -0.83
    }}%
    -0.83
    <h1>
    -0.82
     latter
    -0.80
    ）。
    -0.78
     appeared
    -0.77
    POSITIVE LOGITS
    )
    1.84
    ")
    1.74
    ())
    1.70
    ')
    1.68
     ")
    1.46
    [])
    1.42
    ']
    1.40
    ”)
    1.38
     '')
    1.36
    _)
    1.34
    Activations Density 0.103%

    No Known Activations