© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110677
    Prev
    Next
    INDEX
    Explanations

    numbers followed by am

    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
     motility
    -0.84
    ächtigen
    -0.78
     understood
    -0.72
     {
    -0.72
     never
    -0.70
    SPP
    -0.70
    âteaux
    -0.69
    Ricardo
    -0.69
    unrecognized
    -0.68
     palsy
    -0.67
    POSITIVE LOGITS
    ghis
    0.78
    onghi
    0.70
    isor
    0.70
    lotta
    0.70
    orgung
    0.69
    нное
    0.69
     sueldo
    0.68
    六十
    0.68
     детьми
    0.68
    suri
    0.67
    Activations Density 0.099%

    No Known Activations