© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44894
    Prev
    Next
    INDEX
    Explanations

    convenience and inconvenience

    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
    '
    -1.98
    selbe
    -1.77
    纮
    -1.72
    mpagne
    -1.69
    "
    -1.58
    ’
    -1.57
    瓛
    -1.54
    箩
    -1.52
    命中
    -1.49
     exper
    -1.45
    POSITIVE LOGITS
    🢒
    2.02
    ]
    1.85
    There
    1.81
    >
    1.81
     namun
    1.80
    tividade
    1.79
    ៚
    1.77
    While
    1.76
    istorante
    1.75
     includes
    1.73
    Activations Density 0.003%

    No Known Activations