© 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. 80595
    Prev
    Next
    INDEX
    Explanations

    Enrique, Scrooge, debugger, shutil

    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
    lossians
    -2.95
    猹
    -2.70
    PreExecute
    -2.47
    ⽌
    -2.38
    慊
    -2.36
    PostExecute
    -2.27
    ⚋
    -2.22
    طبيق
    -2.22
     impedir
    -2.16
    Comté
    -2.13
    POSITIVE LOGITS
     usado
    2.63
     weathered
    2.52
     was
    2.44
     I
    2.39
    のだが
    2.33
    j
    2.30
    z
    2.28
     ‘’
    2.27
    …….
    2.23
    在他
    2.23
    Activations Density 0.010%

    No Known Activations