© 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. 14938
    Prev
    Next
    INDEX
    Explanations

    numbers and labels

    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
     mediu
    -0.91
     мир
    -0.90
    pady
    -0.89
    つづく
    -0.88
     There
    -0.86
     fone
    -0.85
    There
    -0.85
     that
    -0.85
     حالات
    -0.84
     It
    -0.84
    POSITIVE LOGITS
     see
    1.36
     ativar
    1.03
    see
    1.03
     discapacidad
    1.00
     réessayer
    1.00
    pplung
    0.99
     např
    0.99
     lehet
    0.98
    も多く
    0.97
     alugar
    0.96
    Activations Density 0.009%

    No Known Activations