© 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. 44342
    Prev
    Next
    INDEX
    Explanations

    peppers and chilies

    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
    お昼
    -1.99
    ଽ
    -1.89
    也有
    -1.88
     ditt
    -1.84
    ’?
    -1.77
    they
    -1.76
     femeninos
    -1.76
    ſelves
    -1.69
     eléctricos
    -1.68
     çerçe
    -1.68
    POSITIVE LOGITS
     Then
    2.27
     By
    2.19
     We
    1.80
     }));
    1.69
     From
    1.69
    简称
    1.66
     }))
    1.66
     Want
    1.65
     To
    1.63
    神器
    1.61
    Activations Density 0.005%

    No Known Activations