© 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. 34-GEMMASCOPE-RES-131K
    7. 1649
    Prev
    Next
    INDEX
    Explanations

    languages and translation

    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_34/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
    intera
    -0.80
     klasy
    -0.79
    ⵡ
    -0.76
     Lordship
    -0.74
    Ir
    -0.73
    ZA
    -0.72
     bekam
    -0.72
     liegenden
    -0.71
    AAC
    -0.71
     ⇒
    -0.71
    POSITIVE LOGITS
     languages
    2.45
    languages
    1.34
     Languages
    1.34
    Languages
    1.28
     idiomas
    1.25
     foreign
    1.17
     multiple
    1.10
     vernacular
    1.04
     langues
    1.04
     language
    1.04
    Activations Density 0.036%

    No Known Activations