© 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. 34-GEMMASCOPE-RES-131K
    7. 32193
    Prev
    Next
    INDEX
    Explanations

    numbers with zeros

    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_34/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
    gül
    -0.81
    ضای
    -0.69
    翡翠
    -0.66
    pří
    -0.66
     педаго
    -0.66
    Веду
    -0.65
    gebnissen
    -0.65
     masyarakat
    -0.64
    Gesture
    -0.63
     sebe
    -0.63
    POSITIVE LOGITS
     дорог
    0.91
    æus
    0.82
     duelo
    0.78
     halbe
    0.78
    gypte
    0.74
     BPI
    0.74
    াহ
    0.73
     Zh
    0.73
     copiar
    0.72
    Nh
    0.72
    Activations Density 0.035%

    No Known Activations