© 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. 34758
    Prev
    Next
    INDEX
    Explanations

    units followed by quantities or rate

    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
    mektedir
    -0.98
    ərbaycan
    -0.93
     spermato
    -0.88
     seksi
    -0.87
     vektör
    -0.83
     jaro
    -0.82
    امه
    -0.82
     Øst
    -0.82
     orna
    -0.81
    Eman
    -0.81
    POSITIVE LOGITS
     viena
    1.00
     wzglę
    0.98
     embarazada
    0.93
    JHEP
    0.93
     också
    0.91
    pendi
    0.91
     your
    0.90
     lekko
    0.90
    
    0.89
    何とか
    0.88
    Activations Density 0.148%

    No Known Activations