© 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. 36086
    Prev
    Next
    INDEX
    Explanations

    access sites

    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
     these
    -1.30
    これらの
    -1.21
    这些
    -1.05
     íntimo
    -1.05
    .
    -1.02
     those
    -1.01
     eloku
    -0.94
     dobře
    -0.94
    ↵↵↵
    -0.93
    饗
    -0.91
    POSITIVE LOGITS
    Donnerstag
    1.09
    toren
    1.09
    蠃
    1.06
    Breite
    1.04
     procede
    1.02
    ICOLON
    1.01
    xmlhttp
    0.98
    bzw
    0.98
    EditText
    0.97
    Veranstal
    0.97
    Activations Density 0.131%

    No Known Activations