© 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. 15275
    Prev
    Next
    INDEX
    Explanations

    purpose or outcome

    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
     hort
    -1.00
    Apis
    -0.97
     giu
    -0.94
     espoir
    -0.93
     soir
    -0.93
     noci
    -0.91
     extrait
    -0.90
    莴
    -0.88
     asus
    -0.87
     chers
    -0.87
    POSITIVE LOGITS
     testGet
    0.99
     arasındaki
    0.97
     get
    0.92
     demonstrate
    0.91
    不同
    0.91
     trying
    0.91
     Handeln
    0.91
     Seeking
    0.88
    urgency
    0.87
     zdoby
    0.86
    Activations Density 0.092%

    No Known Activations