© 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. 113669
    Prev
    Next
    INDEX
    Explanations

    verbs in Spanish and Portuguese

    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
    ="
    -2.50
    ,"
    -2.48
    的一个
    -2.47
    可以
    -2.38
    3
    -2.36
    应该
    -2.27
    ков
    -2.25
    更
    -2.20
    ]
    -2.20
    和
    -2.17
    POSITIVE LOGITS
    ܃
    2.47
    d
    2.41
    n
    2.30
    
    2.27
    discussed
    2.19
    嫫
    2.19
    represents
    2.16
    獁
    2.13
    慙
    2.09
     soud
    2.08
    Activations Density 0.002%

    No Known Activations