© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60594
    Prev
    Next
    INDEX
    Explanations

    words starting with i, io

    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
     awful
    -2.67
    g
    -2.48
     halben
    -2.44
     outraged
    -2.39
     allzu
    -2.34
     decorada
    -2.34
    倨
    -2.31
    จริง
    -2.30
     verdaderas
    -2.23
    \
    -2.20
    POSITIVE LOGITS
    geſ
    3.00
    鳊
    2.44
    other
    2.39
    ╽
    2.34
     promove
    2.34
     serão
    2.33
    ?"
    2.31
    产生了
    2.28
     kompatibel
    2.28
     acidente
    2.28
    Activations Density 0.003%

    No Known Activations