© 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. 22-GEMMASCOPE-RES-131K
    7. 39488
    Prev
    Next
    INDEX
    Explanations

    mathematical structure and classification

    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
    稲田
    -1.09
     possibilidade
    -1.07
    々の
    -1.02
    ANSW
    -0.99
     tohto
    -0.98
    ญี่ป
    -0.96
    ’
    -0.96
    öy
    -0.96
     SEVENTH
    -0.95
     أكتوبر
    -0.92
    POSITIVE LOGITS
     with
    1.32
     one
    1.30
     something
    1.25
     some
    1.17
     a
    1.11
    某
    1.08
    pectives
    1.02
    某个
    1.00
     without
    0.97
     family
    0.96
    Activations Density 0.028%

    No Known Activations