© 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. 11274
    Prev
    Next
    INDEX
    Explanations

    entity is described or quantified

    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
     that
    -1.66
     then
    -1.27
    Fordítás
    -1.09
     until
    -1.07
     usati
    -0.93
     zrozum
    -0.93
    無事
    -0.92
     jesteśmy
    -0.92
     vergeten
    -0.90
    Tại
    -0.90
    POSITIVE LOGITS
     العديد
    1.14
    various
    1.12
    способ
    1.03
     keinerlei
    1.01
    各种
    1.00
     ``
    0.99
     viewWillAppear
    0.98
     الشخص
    0.96
    bilité
    0.96
    reply
    0.96
    Activations Density 0.075%

    No Known Activations