© 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. 104846
    Prev
    Next
    INDEX
    Explanations

    need for something

    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
    得罪
    -1.16
     bénéfice
    -1.14
    probably
    -1.12
     preescolar
    -1.11
    earlier
    -1.11
    despite
    -1.10
    plenty
    -1.09
    哏
    -1.08
     Sünde
    -1.08
    entire
    -1.06
    POSITIVE LOGITS
     that
    1.98
     which
    1.84
     does
    1.66
     for
    1.63
     with
    1.62
     to
    1.62
     who
    1.48
     whose
    1.47
     after
    1.44
     when
    1.43
    Activations Density 0.170%

    No Known Activations