© 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. 15164
    Prev
    Next
    INDEX
    Explanations

    preserve

    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
    罍
    -3.22
    ৢ
    -3.09
    嫑
    -3.05
    蠵
    -2.73
    鹩
    -2.64
    ᠂
    -2.45
    牁
    -2.42
    휀
    -2.41
    
    -2.39
     Konsequ
    -2.38
    POSITIVE LOGITS
    It
    3.09
    o
    2.47
    There
    2.45
    …..
    2.42
     demonstrate
    2.39
     dasarnya
    2.39
    Despite
    2.36
    ,…
    2.36
    ….
    2.31
    Surprisingly
    2.31
    Activations Density 0.005%

    No Known Activations