© 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. 68972
    Prev
    Next
    INDEX
    Explanations

    dates and names

    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
     to
    -1.48
    を
    -1.38
    などの
    -1.14
     as
    -1.13
     on
    -1.08
    が
    -1.08
     самым
    -1.07
    ～～
    -1.06
    ERÍA
    -1.03
     becomes
    -1.02
    POSITIVE LOGITS
    譴
    1.39
    なのかな
    1.38
    ところは
    1.27
    ところに
    1.25
    色々
    1.23
    ときの
    1.22
     Ties
    1.21
    だと思う
    1.18
    久し
    1.18
    なんですね
    1.17
    Activations Density 0.003%

    No Known Activations