© 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. 109222
    Prev
    Next
    INDEX
    Explanations

    Q: followed by

    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
     Ordo
    -0.85
     Ел
    -0.80
     thoſe
    -0.79
    писи
    -0.78
    糨
    -0.74
    mein
    -0.72
    思います
    -0.72
    logna
    -0.72
     technologically
    -0.72
     viaggi
    -0.72
    POSITIVE LOGITS
     two
    0.82
    akir
    0.79
    上一
    0.75
    τρ
    0.74
     while
    0.73
    творення
    0.71
     geste
    0.71
     several
    0.70
     where
    0.70
     १
    0.69
    Activations Density 0.000%

    No Known Activations