© 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. 34-GEMMASCOPE-RES-131K
    7. 117240
    Prev
    Next
    INDEX
    Explanations

    *-ous or -ousness suffixes

    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_34/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
     Na
    -0.91
     Ni
    -0.84
     uma
    -0.81
    ag
    -0.81
     something
    -0.79
    gen
    -0.79
     Og
    -0.79
     Jo
    -0.79
     mention
    -0.79
     Back
    -0.78
    POSITIVE LOGITS
    ous
    1.64
    ously
    1.38
    OUS
    1.37
    UOUS
    0.93
    Пет
    0.90
    ousness
    0.89
     ous
    0.87
    usnya
    0.87
     fous
    0.84
     دقی
    0.83
    Activations Density 0.113%

    No Known Activations