© 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. 67425
    Prev
    Next
    INDEX
    Explanations

    legal outcomes and final results

    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
     new
    -1.31
     now
    -1.13
     دخترانه
    -1.11
     тонн
    -1.11
     neuen
    -1.04
     neque
    -1.03
    ‌آم
    -1.03
     αὐ
    -1.01
     Erste
    -1.01
     like
    -1.00
    POSITIVE LOGITS
     eventually
    2.13
     later
    1.95
    eventually
    1.88
     subsequently
    1.63
     ultimately
    1.59
    later
    1.50
    后来
    1.50
     finalement
    1.48
    最终
    1.48
     später
    1.48
    Activations Density 0.032%

    No Known Activations