© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 29000
    Prev
    Next
    INDEX
    Explanations

    what does

    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
    ↵
    -1.63
     nació
    -1.56
     probablement
    -1.52
     estará
    -1.49
    );
    -1.48
     cial
    -1.45
     как
    -1.44
     seperti
    -1.40
     либо
    -1.40
     será
    -1.39
    POSITIVE LOGITS
     this
    1.57
     different
    1.44
     stumble
    1.41
    مدیر
    1.38
     any
    1.36
    اشق
    1.34
    珅
    1.34
     gelb
    1.31
     paradas
    1.30
    ühne
    1.30
    Activations Density 0.039%

    No Known Activations