© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27453
    Prev
    Next
    INDEX
    Explanations

    internationalization and code structure

    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
    ząca
    -1.09
     Allez
    -1.09
     ideje
    -1.07
     Personne
    -1.04
    ⼈
    -1.03
    okra
    -1.02
    噼
    -1.02
    蒟
    -1.02
    瞼
    -1.02
     Fórmula
    -1.01
    POSITIVE LOGITS
    the
    1.34
     revenir
    1.17
     and
    1.09
     …
    1.08
    astronomie
    1.07
    -};
    1.05
     sorpresas
    1.05
     possíveis
    1.04
     verho
    1.01
     mudanças
    1.00
    Activations Density 0.206%

    No Known Activations