© 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. 13352
    Prev
    Next
    INDEX
    Explanations

    first person and you

    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
     on
    -1.37
     bahkan
    -1.36
     our
    -1.33
     you
    -1.32
     many
    -1.27
     siguió
    -1.23
     sogar
    -1.22
     karena
    -1.20
     hablaba
    -1.18
     recientemente
    -1.17
    POSITIVE LOGITS
    usually
    1.44
    trying
    1.27
    探讨
    1.27
    known
    1.26
     інші
    1.22
    preferably
    1.22
     brachten
    1.21
    天氣
    1.20
    took
    1.20
     tarea
    1.20
    Activations Density 0.110%

    No Known Activations