© 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. 22-GEMMASCOPE-RES-131K
    7. 72702
    Prev
    Next
    INDEX
    Explanations

    specific names and labels

    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_22/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
     также
    -0.92
     gegen
    -0.91
    邉
    -0.83
     by
    -0.82
    Autriche
    -0.81
     mert
    -0.80
    ição
    -0.79
     Же
    -0.78
    Jangan
    -0.77
     hogy
    -0.77
    POSITIVE LOGITS
     LIBRAR
    1.00
     APPELLANT
    0.96
     Vege
    0.95
     denso
    0.94
    ずみ
    0.89
     MUSICAL
    0.87
     CARTOON
    0.84
    无疑
    0.84
    iverr
    0.84
     marea
    0.83
    Activations Density 0.004%

    No Known Activations