© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 104434
    Prev
    Next
    INDEX
    Explanations

    code references and identifiers

    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
     of
    -1.41
     而
    -1.20
     是
    -1.12
     conclude
    -1.09
     in
    -1.09
     は
    -1.08
     (
    -1.05
    ↵↵
    -1.05
    に
    -1.03
     L
    -1.00
    POSITIVE LOGITS
    فیلم
    1.50
    Kval
    1.40
    Kontak
    1.40
     expérimentés
    1.38
    Harga
    1.38
    Sản
    1.38
    鲥
    1.37
    kepada
    1.34
    Нам
    1.32
    Гео
    1.30
    Activations Density 0.005%

    No Known Activations