© 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. 64828
    Prev
    Next
    INDEX
    Explanations

    programming class definitions

    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
     همچنین
    -1.28
    
    -1.06
     देश
    -1.02
    无需
    -1.02
    JOSEPH
    -1.02
     ©️
    -1.02
     سپس
    -1.02
    見えます
    -1.00
     commode
    -1.00
     :—
    -0.99
    POSITIVE LOGITS
     example
    1.20
     tė
    1.20
     gyvento
    1.19
     этаж
    1.15
     aukš
    1.09
    //};
    1.09
     tikra
    1.06
    4
    1.05
    2
    1.05
     Example
    1.05
    Activations Density 0.012%

    No Known Activations