© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 35955
    Prev
    Next
    INDEX
    Explanations

    features for upcoming film

    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
     Auffassung
    -1.30
     .......
    -1.23
    -\\
    -1.23
    絎
    -1.22
     ہے۔
    -1.19
    ivity
    -1.19
     pourront
    -1.18
     DAVID
    -1.14
     overly
    -1.14
     .........
    -1.13
    POSITIVE LOGITS
     noteworthy
    1.38
     poignant
    1.36
     perplexing
    1.34
     difficult
    1.34
     rigorous
    1.30
     endearing
    1.27
     horrific
    1.26
     preventing
    1.25
     mammoth
    1.24
     more
    1.23
    Activations Density 0.024%

    No Known Activations