© 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. 10-GEMMASCOPE-RES-131K
    7. 66460
    Prev
    Next
    INDEX
    Explanations

    software development terms

    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_10/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
    itinéraire
    -1.16
     takže
    -1.15
    最重要
    -1.11
     zejména
    -1.11
     даже
    -1.10
     Beschluss
    -1.10
    QUICK
    -1.09
     Often
    -1.09
     This
    -1.09
     mediodía
    -1.08
    POSITIVE LOGITS
     autre
    1.22
    ++)
    1.22
    ᠵ
    1.20
    gidas
    1.20
    aczy
    1.20
     historie
    1.18
     employés
    1.16
     JAXBElement
    1.16
    ())
    1.14
     mdi
    1.14
    Activations Density 0.029%

    No Known Activations