© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81351
    Prev
    Next
    INDEX
    Explanations

    English and foreign words

    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
    ński
    -0.90
    応
    -0.88
    iture
    -0.81
    ensione
    -0.81
    éos
    -0.79
    vanced
    -0.78
     UMKM
    -0.78
    ionales
    -0.77
    apha
    -0.77
    ENSITY
    -0.77
    POSITIVE LOGITS
     필요
    0.88
    ignons
    0.79
    桜
    0.77
     jeep
    0.77
     propositions
    0.77
     semicirc
    0.74
     díl
    0.74
     Ebay
    0.74
     enough
    0.74
     Mastercard
    0.74
    Activations Density 0.006%

    No Known Activations