© 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. 10-GEMMASCOPE-RES-131K
    7. 105688
    Prev
    Next
    INDEX
    Explanations

    need to do something

    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_10/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
    l
    -1.66
    3
    -1.63
    1
    -1.60
    </h3>
    -1.57
     they
    -1.52
    O
    -1.52
    2
    -1.47
    7
    -1.45
    B
    -1.43
    这
    -1.38
    POSITIVE LOGITS
     zarówno
    1.56
    夤
    1.54
     that
    1.52
     aast
    1.43
     istimewa
    1.43
     delito
    1.41
    錚
    1.40
     kõ
    1.39
    UTIVE
    1.39
    *}\
    1.38
    Activations Density 0.009%

    No Known Activations