© 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. 128215
    Prev
    Next
    INDEX
    Explanations

    reality show

    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
    5
    -2.20
    ⢅
    -2.13
    
    -2.02
     ∼
    -1.96
     уви
    -1.88
    玊
    -1.86
    2
    -1.86
    紧接着
    -1.82
    ції
    -1.82
    9
    -1.80
    POSITIVE LOGITS
    {
    2.14
    e
    2.03
     
    1.98
    .
    1.92
     reality
    1.92
     you
    1.89
    岐阜
    1.86
    昪
    1.86
    呖
    1.84
    But
    1.80
    Activations Density 0.012%

    No Known Activations