© 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. 27560
    Prev
    Next
    INDEX
    Explanations

    quantifiers and generality

    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
    ofollow
    -0.88
     нашем
    -0.88
     kilos
    -0.87
    antart
    -0.84
    fdb
    -0.84
     infek
    -0.82
     соответствует
    -0.82
     morire
    -0.81
     těchto
    -0.80
    lenir
    -0.80
    POSITIVE LOGITS
     any
    2.50
    any
    1.62
     all
    1.60
     любого
    1.39
     cualquier
    1.38
     every
    1.37
     several
    1.35
    Any
    1.34
     qualquer
    1.33
     cualquiera
    1.33
    Activations Density 0.021%

    No Known Activations