© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12672
    Prev
    Next
    INDEX
    Explanations

    code execution and data manipulation

    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
    Other
    -0.89
    Several
    -0.82
     Other
    -0.82
     other
    -0.81
    خص
    -0.77
     Several
    -0.76
    üedad
    -0.75
     several
    -0.75
     Lainnya
    -0.74
    verted
    -0.73
    POSITIVE LOGITS
     thêm
    0.87
     Tanks
    0.85
     REPORTER
    0.85
     again
    0.84
     Electrode
    0.83
     previously
    0.81
    naj
    0.80
    FRIDAY
    0.79
     إضافة
    0.78
     already
    0.77
    Activations Density 0.024%

    No Known Activations