© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38738
    Prev
    Next
    INDEX
    Explanations

    plist key-value pairs

    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
     them
    -0.98
    Any
    -0.93
     inapropiados
    -0.91
    Furthermore
    -0.91
    それを
    -0.90
    出した
    -0.90
    並且
    -0.89
     wszel
    -0.89
    并且
    -0.88
    Moreover
    -0.86
    POSITIVE LOGITS
    良し
    1.03
     bamb
    1.00
     ─
    0.96
     Richelieu
    0.94
     coni
    0.92
    洼
    0.91
    Esprit
    0.91
    比較的
    0.90
    código
    0.90
    isFirst
    0.89
    Activations Density 0.002%

    No Known Activations