© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30924
    Prev
    Next
    INDEX
    Explanations

    por followed by specific endings

    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
    çası
    -0.95
     Realistic
    -0.79
     bahawa
    -0.75
    餡
    -0.75
     meille
    -0.73
    imoto
    -0.71
    認め
    -0.71
     akzeptieren
    -0.69
     halved
    -0.69
    iddhartha
    -0.68
    POSITIVE LOGITS
    Por
    1.41
     por
    1.29
    por
    1.26
    POR
    1.23
     Por
    1.22
     POR
    1.11
     Пор
    1.07
     PORT
    0.96
    pora
    0.94
    cul
    0.91
    Activations Density 0.042%

    No Known Activations