© 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. 118740
    Prev
    Next
    INDEX
    Explanations

    made for a purpose

    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
     "
    -1.66
     Berücksich
    -1.52
    袿
    -1.45
     include
    -1.45
    ̀
    -1.39
     OGSÅ
    -1.38
     肩
    -1.38
     abbiamo
    -1.34
     verfügen
    -1.33
     vengono
    -1.31
    POSITIVE LOGITS
    ↵
    1.48
     調査
    1.42
     profond
    1.34
    In
    1.30
     to
    1.29
    in
    1.27
    庒
    1.27
    此外
    1.26
     be
    1.25
    accompag
    1.25
    Activations Density 0.031%

    No Known Activations