© 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. 39829
    Prev
    Next
    INDEX
    Explanations

    actions leading to outcomes

    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
    因为它
    -1.54
    同时也
    -1.53
     It
    -1.41
     mantiene
    -1.40
     mehrfach
    -1.38
    这点
    -1.37
     zároveň
    -1.34
    指的是
    -1.34
     vielfach
    -1.31
    それも
    -1.30
    POSITIVE LOGITS
     and
    1.67
     their
    1.49
     the
    1.42
     projekt
    1.41
     specifik
    1.37
     dör
    1.36
     a
    1.28
     such
    1.28
     fön
    1.24
     sprüche
    1.22
    Activations Density 0.163%

    No Known Activations