© 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. 10-GEMMASCOPE-RES-131K
    7. 59002
    Prev
    Next
    INDEX
    Explanations

    of followed by noun phrase

    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
     biß
    -1.65
     hodiny
    -1.48
     hilos
    -1.44
    อื่น
    -1.43
    悫
    -1.39
     červená
    -1.38
     aquellas
    -1.37
     hjemmeside
    -1.35
    dersfield
    -1.34
     spotless
    -1.34
    POSITIVE LOGITS
     of
    1.96
     who
    1.83
     this
    1.55
     και
    1.54
    ності
    1.52
     each
    1.52
     whose
    1.51
     tortas
    1.51
     balcon
    1.49
    焢
    1.48
    Activations Density 0.077%

    No Known Activations