© 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. 20326
    Prev
    Next
    INDEX
    Explanations

    nonprofit and tax-exempt organizations

    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
     APPLICABLE
    -1.52
     ;
    -1.51
    ton
    -1.46
     ARISING
    -1.32
    ?
    -1.29
     :
    -1.29
    平时
    -1.26
    圌
    -1.26
    tin
    -1.23
    chenta
    -1.23
    POSITIVE LOGITS
     without
    1.20
     at
    1.18
    pompa
    1.15
     on
    1.12
     waarschijnlijk
    1.08
    钜
    1.08
     zelfs
    1.07
    letzt
    1.07
     Unlike
    1.06
    cartão
    1.05
    Activations Density 0.042%

    No Known Activations