© 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. 73814
    Prev
    Next
    INDEX
    Explanations

    found a solution

    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
     ersten
    -1.04
     primeira
    -1.04
     första
    -0.94
     eerste
    -0.91
     is
    -0.86
     erster
    -0.85
     первый
    -0.84
    就开始
    -0.84
     erstmals
    -0.84
     Producing
    -0.81
    POSITIVE LOGITS
     finalement
    1.44
    結局
    1.33
     ultimately
    1.08
     solutions
    1.05
     solution
    1.05
     eventually
    1.02
    resolved
    1.00
     resolved
    0.98
     decid
    0.97
     decided
    0.95
    Activations Density 0.061%

    No Known Activations