© 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. 14275
    Prev
    Next
    INDEX
    Explanations

    times

    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
    詎
    -2.53
    ༵
    -2.53
     grijs
    -2.39
    ୈ
    -2.39
     mutta
    -2.31
    但却
    -2.28
     roja
    -2.25
    狆
    -2.23
    
    -2.23
    蚴
    -2.20
    POSITIVE LOGITS
    )
    2.34
    訁
    2.28
     vez
    2.14
     delightfully
    2.13
    times
    2.06
     necesario
    2.03
     放題
    2.00
     '
    1.98
    !!!!!!
    1.98
    hline
    1.95
    Activations Density 0.001%

    No Known Activations