© 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. 41664
    Prev
    Next
    INDEX
    Explanations

    punctuation separators

    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
     is
    -2.38
    硖
    -2.34
     example
    -2.03
     Belakang
    -1.94
    栒
    -1.89
     case
    -1.88
    N
    -1.84
     then
    -1.83
     schöner
    -1.81
     start
    -1.80
    POSITIVE LOGITS
    ︕
    2.28
    饜
    2.06
    齶
    2.00
    就像是
    1.98
    </td>
    1.96
    鷽
    1.93
    豋
    1.88
    踽
    1.85
    ⎘
    1.84
    慙
    1.78
    Activations Density 0.014%

    No Known Activations