© 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. 22-GEMMASCOPE-RES-131K
    7. 79670
    Prev
    Next
    INDEX
    Explanations

    who questions

    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_22/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
     need
    -1.72
     want
    -1.47
     experiences
    -1.43
     another
    -1.35
     use
    -1.35
     will
    -1.29
     something
    -1.29
    ↵↵
    -1.24
     that
    -1.23
     feel
    -1.23
    POSITIVE LOGITS
    whom
    1.40
    ︕
    1.27
    whose
    1.27
     göm
    1.26
     kimdir
    1.23
     who
    1.23
     ネタバレ
    1.23
    ㈩
    1.22
    逐渐
    1.19
    referred
    1.19
    Activations Density 0.013%

    No Known Activations