© 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. 14590
    Prev
    Next
    INDEX
    Explanations

    first name, surname, middle name

    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
    
    -1.09
    𝑓
    -1.04
    `(
    -1.02
    /</
    -0.96
     there
    -0.96
     bởi
    -0.96
    鳥居
    -0.94
     ри
    -0.94
    "#
    -0.94
    зва
    -0.94
    POSITIVE LOGITS
     his
    1.09
     comunicare
    1.06
    çamento
    1.06
     spannende
    1.03
     intrusions
    1.00
     entgeg
    1.00
    YOND
    0.98
    rekte
    0.98
     kroppen
    0.98
    怅
    0.98
    Activations Density 0.002%

    No Known Activations