© 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. 34-GEMMASCOPE-RES-131K
    7. 48781
    Prev
    Next
    INDEX
    Explanations

    the word "the" followed by a noun

    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
    ánt
    -0.81
     anbieten
    -0.75
    inkled
    -0.74
    oni
    -0.74
    ladolid
    -0.73
    Sofa
    -0.73
     кілька
    -0.73
     состоит
    -0.71
    rassed
    -0.71
     biopsies
    -0.71
    POSITIVE LOGITS
     mountainous
    0.73
    MODULE
    0.71
     animale
    0.69
    ophosphate
    0.69
     Module
    0.69
     core
    0.68
     математи
    0.67
     musicale
    0.67
     моду
    0.67
    fourth
    0.66
    Activations Density 0.032%

    No Known Activations