© 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. 64657
    Prev
    Next
    INDEX
    Explanations

    json keys and values

    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
     dollari
    -1.29
    🤠
    -1.16
    💓
    -1.13
     Portugu
    -1.10
    tionally
    -1.09
    getLastName
    -1.09
    🤪
    -1.09
    🤙
    -1.09
    🤞
    -1.09
     americano
    -1.07
    POSITIVE LOGITS
     possibilità
    1.22
     énfasis
    1.19
     establecidos
    1.17
     pôr
    1.17
     observaciones
    1.17
     konkrét
    1.16
     takich
    1.16
     accesorio
    1.12
     olhar
    1.10
     crescimento
    1.10
    Activations Density 0.013%

    No Known Activations