© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33900
    Prev
    Next
    INDEX
    Explanations

    Get information, advice, or to acquire 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_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
     other
    -1.30
     üblichen
    -1.29
     vano
    -1.12
     governador
    -1.09
     alrededores
    -1.09
     that
    -1.09
    ɟ
    -1.09
     attesa
    -1.08
    felizmente
    -1.07
    อื่น
    -1.06
    POSITIVE LOGITS
     your
    1.28
    ,
    1.20
     oluyor
    1.09
     tässä
    1.09
    chemise
    1.09
    ны
    1.08
     számára
    1.07
     például
    1.06
     yourself
    1.05
    TION
    1.05
    Activations Density 0.045%

    No Known Activations