© 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. 73094
    Prev
    Next
    INDEX
    Explanations

    hardware control commands

    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
     dodatk
    -1.31
     esprits
    -1.26
    После
    -1.23
    њу
    -1.23
     journalistes
    -1.20
    useNewUrlParser
    -1.18
    Depois
    -1.17
    karni
    -1.16
    んでいた
    -1.16
     olması
    -1.16
    POSITIVE LOGITS
    .
    1.24
     commands
    1.22
    =$((
    1.18
     today
    1.17
     to
    1.15
    要望
    1.15
    bảng
    1.09
    しみ
    1.09
    arctan
    1.09
     says
    1.07
    Activations Density 0.043%

    No Known Activations