© 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. 10-GEMMASCOPE-RES-131K
    7. 100037
    Prev
    Next
    INDEX
    Explanations

    "I" statements of action or feeling

    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
     också
    -1.59
     cũng
    -1.49
    也
    -1.47
     también
    -1.45
     some
    -1.34
     also
    -1.34
     também
    -1.32
     alcuni
    -1.31
     yep
    -1.30
    某些
    -1.29
    POSITIVE LOGITS
    förm
    1.39
    our
    1.37
    beitung
    1.34
    未來
    1.27
     nostra
    1.26
     sær
    1.24
    monių
    1.24
    翾
    1.23
    思议
    1.23
     terza
    1.23
    Activations Density 0.050%

    No Known Activations