© 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. 34-GEMMASCOPE-RES-131K
    7. 115796
    Prev
    Next
    INDEX
    Explanations

    line references

    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_34/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
    Iné
    -0.85
    児童
    -0.79
     shaken
    -0.79
     genuinely
    -0.78
    錡
    -0.77
     швид
    -0.76
     افزار
    -0.76
    ība
    -0.75
     joie
    -0.73
    tamia
    -0.73
    POSITIVE LOGITS
     line
    1.17
     lines
    1.06
     Lines
    0.97
    line
    0.94
    lines
    0.91
     Line
    0.86
    oooo
    0.83
     EFE
    0.82
    hydro
    0.81
     LINES
    0.81
    Activations Density 0.002%

    No Known Activations