© 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. 130725
    Prev
    Next
    INDEX
    Explanations

    the followed by specific entities or events

    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
     sooo
    -2.28
     soooo
    -2.25
     !!!!
    -2.19
    媵
    -1.97
     somente
    -1.93
     Dinas
    -1.92
     itself
    -1.91
    有任何
    -1.89
    mainly
    -1.88
    primarily
    -1.88
    POSITIVE LOGITS
     with
    2.31
     meticulous
    2.27
     sizeable
    2.23
     plethora
    2.19
     frantic
    2.16
     bolster
    2.16
     seven
    2.16
     for
    2.14
     slight
    2.11
     strange
    2.11
    Activations Density 0.030%

    No Known Activations