© 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. 75721
    Prev
    Next
    INDEX
    Explanations

    copyright notices and file paths

    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
     critica
    -1.09
     legislat
    -0.97
     freg
    -0.96
     beneficia
    -0.94
     abus
    -0.92
     efic
    -0.91
     acom
    -0.90
     tabel
    -0.86
    ".$_
    -0.85
     patria
    -0.85
    POSITIVE LOGITS
     =
    1.17
     is
    1.01
     then
    0.95
     concepción
    0.84
    SE
    0.84
     producido
    0.82
    utal
    0.81
    zi
    0.79
    enumi
    0.79
    .;
    0.79
    Activations Density 0.000%

    No Known Activations