© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74602
    Prev
    Next
    INDEX
    Explanations

    `VALUE`, `fadeOut`, `PAGE`, `Nakamura`, `ADDR`

    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
    ).
    -2.98
    錘
    -2.61
    ?
    -2.47
     ocurrir
    -2.44
     związane
    -2.34
     çünkü
    -2.33
    危險
    -2.27
     incessant
    -2.27
     cubierto
    -2.23
     impeccable
    -2.22
    POSITIVE LOGITS
    ?”
    3.48
    ;
    3.05
    м
    2.77
    的
    2.61
    which
    2.50
    i
    2.50
    .
    2.36
     uſed
    2.31
     mits
    2.31
    es
    2.31
    Activations Density 0.009%

    No Known Activations