© 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. 130945
    Prev
    Next
    INDEX
    Explanations

    code curly braces and symbols

    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
    ACHUSETTS
    -1.10
     auswählen
    -1.05
    zkopf
    -1.00
     parfois
    -1.00
     ráp
    -0.99
    igth
    -0.97
    cnia
    -0.96
    などが
    -0.96
    rdoba
    -0.95
     señala
    -0.95
    POSITIVE LOGITS
     it
    0.99
    感じで
    0.90
     It
    0.89
     there
    0.87
    感じです
    0.86
    ）.
    0.84
     There
    0.83
    感じが
    0.82
    気がする
    0.82
    😹
    0.81
    Activations Density 0.005%

    No Known Activations