© 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. 98323
    Prev
    Next
    INDEX
    Explanations

    positive introductions or descriptions

    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
     that
    -1.32
     it
    -1.23
    ortic
    -1.20
     there
    -1.13
    Waterproof
    -1.06
    っちゃった
    -0.99
     QUÉ
    -0.99
     their
    -0.98
     what
    -0.98
     prière
    -0.97
    POSITIVE LOGITS
     savu
    1.13
     verhe
    1.12
     cilvē
    1.07
     šo
    1.05
     dieną
    1.04
     ตั้ง
    1.04
    achter
    1.02
     tämä
    1.02
    вих
    1.00
     daudz
    1.00
    Activations Density 0.005%

    No Known Activations