© 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. 10-GEMMASCOPE-RES-131K
    7. 47660
    Prev
    Next
    INDEX
    Explanations

    logic and related concepts

    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_10/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
    厚度
    -1.26
     naam
    -1.25
    "'
    -1.24
    mán
    -1.23
    joner
    -1.22
    ней
    -1.20
     which
    -1.19
     ★★★★★
    -1.18
    endió
    -1.18
     because
    -1.18
    POSITIVE LOGITS
     няколко
    1.27
     когато
    1.27
     каждом
    1.21
     לכל
    1.20
    opheles
    1.17
     fuertes
    1.16
    新しく
    1.16
     кръ
    1.14
     anything
    1.13
    xymatrix
    1.13
    Activations Density 0.029%

    No Known Activations