© 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. 90282
    Prev
    Next
    INDEX
    Explanations

    object identifiers and properties

    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
    0
    -4.59
    ↵↵
    -3.11
    瑧
    -2.41
    祆
    -2.23
    »,
    -2.23
     temer
    -2.20
     We
    -2.20
    1
    -2.17
     \
    -2.14
    i
    -2.09
    POSITIVE LOGITS
    をしています
    2.64
     Todas
    2.63
     setelan
    2.50
    梠
    2.47
     Descub
    2.47
     Otras
    2.33
     swoop
    2.27
    是
    2.27
     spou
    2.20
    鵙
    2.20
    Activations Density 0.001%

    No Known Activations