© 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. 74846
    Prev
    Next
    INDEX
    Explanations

    contrasting or complementary pairs

    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
     objekt
    -1.42
    مث
    -1.39
     -¿
    -1.37
     gancho
    -1.36
     their
    -1.35
     the
    -1.32
     other
    -1.30
     vean
    -1.29
     käytt
    -1.29
     amplificador
    -1.28
    POSITIVE LOGITS
     to
    2.03
     also
    1.80
     también
    1.77
     cũng
    1.60
    事も
    1.58
     of
    1.53
     breathtaking
    1.48
    也会
    1.48
     picturesque
    1.47
    事が
    1.46
    Activations Density 0.086%

    No Known Activations