© 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. 26359
    Prev
    Next
    INDEX
    Explanations

    section headers and starters

    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
     ofici
    -1.20
    等我
    -1.19
     menggunakan
    -1.18
     gober
    -1.15
     anún
    -1.13
    
    -1.11
    otropy
    -1.09
     viac
    -1.09
     origini
    -1.05
    𖧵
    -1.05
    POSITIVE LOGITS
     then
    1.18
     again
    1.01
    然后
    0.94
     опять
    0.94
     затем
    0.92
     followed
    0.91
     nuevamente
    0.86
     Drawings
    0.84
     prophets
    0.83
     снова
    0.83
    Activations Density 0.003%

    No Known Activations