© 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. 74867
    Prev
    Next
    INDEX
    Explanations

    global + topics

    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
     than
    -1.88
    ܔ
    -1.80
     trám
    -1.77
    珦
    -1.74
     cewek
    -1.73
    盦
    -1.72
    衚
    -1.72
     城市
    -1.71
    🧏
    -1.68
     célè
    -1.67
    POSITIVE LOGITS
     of
    2.55
     
    1.71
    :
    1.66
    |
    1.65
    *
    1.51
    ]
    1.48
    !
    1.44
    /
    1.44
     он
    1.43
    <blockquote>
    1.35
    Activations Density 0.035%

    No Known Activations