© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15236
    Prev
    Next
    INDEX
    Explanations

    newly formed states

    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
     today
    -1.84
     last
    -1.38
     yesterday
    -1.32
     oggi
    -1.27
     here
    -1.23
     aujourd
    -1.22
     tonight
    -1.21
     can
    -1.12
    oggi
    -1.11
    去年
    -1.09
    POSITIVE LOGITS
     hadn
    1.62
     havia
    1.59
     habían
    1.54
     تازه
    1.53
     وكان
    1.52
     sedang
    1.52
     estava
    1.51
     had
    1.46
     había
    1.45
    กำลัง
    1.45
    Activations Density 0.095%

    No Known Activations