© 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. 33518
    Prev
    Next
    INDEX
    Explanations

    tokens before prepositions or articles

    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
    gamma
    -1.10
    `
    -0.96
    <b>
    -0.93
     schooling
    -0.93
    <u>
    -0.92
    else
    -0.89
    搐
    -0.88
    </b>
    -0.84
    a
    -0.83
     while
    -0.82
    POSITIVE LOGITS
     Dür
    1.29
     인터
    1.20
     leggera
    1.11
     utilizzati
    1.10
     immagini
    1.08
     difficoltà
    1.07
     buone
    1.07
    úmero
    1.07
    എ
    1.06
     também
    1.05
    Activations Density 0.169%

    No Known Activations