© 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. 73068
    Prev
    Next
    INDEX
    Explanations

    place names

    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
     deklar
    -1.15
    electron
    -1.07
    ᶤ
    -1.02
     konfer
    -1.01
     kontrak
    -0.99
    objet
    -0.98
    戰爭
    -0.98
    addTab
    -0.98
    ائدة
    -0.97
    ATUM
    -0.96
    POSITIVE LOGITS
    ણી
    0.94
    ᐛ
    0.91
    尤其
    0.90
    automne
    0.90
    倡
    0.88
     传统
    0.88
    ера
    0.86
     医院
    0.84
     Если
    0.84
     thậm
    0.83
    Activations Density 0.010%

    No Known Activations