© 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. 10-GEMMASCOPE-RES-131K
    7. 59830
    Prev
    Next
    INDEX
    Explanations

    Distinguished Professor, firstName

    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
     antaranya
    -2.95
     "
    -2.88
    y
    -2.86
    antaranya
    -2.78
    毉
    -2.75
    ).
    -2.70
    =
    -2.63
    ):
    -2.59
     leaped
    -2.58
     hadapan
    -2.53
    POSITIVE LOGITS
    ︕
    3.16
    ⛦
    3.08
    ſſen
    3.03
    豨
    2.86
    猹
    2.73
    ܆
    2.72
    ჻
    2.67
    艫
    2.61
    ｱ
    2.59
    秶
    2.59
    Activations Density 0.001%

    No Known Activations