© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 13308
    Prev
    Next
    INDEX
    Explanations

    adding computational constructs

    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
     nabi
    -1.09
     maniere
    -1.06
     teater
    -1.05
     بشأن
    -1.01
     étages
    -1.01
     milj
    -0.98
     zove
    -0.97
     verden
    -0.96
     ungdom
    -0.94
     fournisseur
    -0.94
    POSITIVE LOGITS
     their
    1.09
     Ո
    0.92
     focusing
    0.89
    ;
    0.86
     using
    0.86
     strategies
    0.85
     useful
    0.83
     auch
    0.82
     tienen
    0.82
     також
    0.82
    Activations Density 0.088%

    No Known Activations