© 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. 43500
    Prev
    Next
    INDEX
    Explanations

    expresses comparisons or degrees

    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
     to
    -2.19
    </i>
    -1.33
     here
    -1.31
     would
    -1.25
     selanjutnya
    -1.21
    疳
    -1.19
     especially
    -1.16
     jika
    -1.16
    Besos
    -1.14
    Դ
    -1.14
    POSITIVE LOGITS
     it
    2.06
     we
    1.71
    それは
    1.41
     than
    1.38
     rechazar
    1.33
     Politiker
    1.28
     ciertas
    1.26
     появится
    1.20
     jako
    1.20
    aving
    1.20
    Activations Density 0.075%

    No Known Activations