© 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. 11158
    Prev
    Next
    INDEX
    Explanations

    kris names

    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
    h
    -2.91
    蜴
    -2.89
     eerie
    -2.86
     newest
    -2.78
    秝
    -2.73
    )}$.
    -2.69
    ⏑
    -2.66
    ijnlijk
    -2.61
     esteemed
    -2.59
     immeasurable
    -2.58
    POSITIVE LOGITS
    er
    2.81
     offizielle
    2.75
    だわ
    2.67
     letzte
    2.56
     ausein
    2.52
    And
    2.48
    selben
    2.45
    mainAxisSize
    2.44
     spost
    2.38
    Suka
    2.34
    Activations Density 0.002%

    No Known Activations