© 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. 11134
    Prev
    Next
    INDEX
    Explanations

    acceptable quality or degree

    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
     berühm
    -1.31
    érons
    -1.28
     こと
    -1.26
     ursprüng
    -1.25
    aneity
    -1.24
     militä
    -1.23
    accesorios
    -1.22
    醅
    -1.21
     pulito
    -1.21
     bytu
    -1.20
    POSITIVE LOGITS
     enough
    1.22
    h
    1.08
    t
    1.07
    '
    0.99
    D
    0.99
    A
    0.97
    k
    0.96
    In
    0.96
    又不
    0.95
     offer
    0.95
    Activations Density 0.021%

    No Known Activations