© 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. 22-GEMMASCOPE-RES-131K
    7. 11250
    Prev
    Next
    INDEX
    Explanations

    example of specific transformation

    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
     invitar
    -1.09
     tradic
    -1.05
    sprzed
    -0.99
    𝓒
    -0.98
     ARXIV
    -0.96
     vaisselle
    -0.96
     typelib
    -0.94
    愍
    -0.90
     интерьере
    -0.89
    skou
    -0.89
    POSITIVE LOGITS
     useful
    1.12
     then
    1.11
     usable
    1.06
     acceptable
    1.01
     will
    0.98
     분석
    0.92
     suitable
    0.91
    te
    0.91
     crucial
    0.91
    )
    0.90
    Activations Density 0.070%

    No Known Activations