© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9036
    Prev
    Next
    INDEX
    Explanations

    SFTP server

    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
     and
    -2.61
    aların
    -1.92
    verre
    -1.80
     richt
    -1.80
    malte
    -1.67
    unser
    -1.66
     Ukraina
    -1.66
     tages
    -1.65
    sprzedam
    -1.60
     staffel
    -1.59
    POSITIVE LOGITS
    着一个
    2.16
     diferencias
    2.16
     ciencias
    1.95
     inaprop
    1.89
    捋
    1.79
     sogar
    1.78
    着一
    1.77
    </h2>
    1.77
     pido
    1.72
     inneces
    1.72
    Activations Density 0.030%

    No Known Activations